© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68649
    Prev
    Next
    INDEX
    Explanations

    components and substances

    np_acts-logits-general · gemini-2.5-flash-lite

    technical words related to data structures or components in computing, biology, or technical fields.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron responds strongly to words naming discrete content or data elements (e.g. article, title, region, element, field, video, audio, data).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     it
    -1.17
    After
    -1.00
     sitä
    -0.92
    🦋
    -0.89
    بو
    -0.88
     líqu
    -0.88
    thenReturn
    -0.87
    的存在
    -0.85
    \}$
    -0.85
    🌻
    -0.84
    POSITIVE LOGITS
    Expertise
    1.09
     verschied
    1.05
     Unterschiede
    0.99
     нынеш
    0.98
     Könige
    0.98
     heutige
    0.97
     katk
    0.95
     Reparatur
    0.95
     ausreich
    0.94
     künftig
    0.94
    Activations Density 0.193%

    No Known Activations