© 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. 12937
    Prev
    Next
    INDEX
    Explanations

    instead, additional, also

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

    The neuron fires on semantically rich content tokens—key nouns, verbs, adjectives, numbers, and technical terms—while largely ignoring common function words.

    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
    是一款
    -1.01
    のある
    -0.90
    杳
    -0.89
     gustar
    -0.88
     who
    -0.88
    ℴ
    -0.87
     tecnologías
    -0.86
     relativamente
    -0.86
     finanzas
    -0.86
    noob
    -0.85
    POSITIVE LOGITS
     instead
    1.70
     additional
    1.42
     also
    1.41
     zusätzlich
    1.34
     вместо
    1.30
     additionally
    1.29
    Instead
    1.25
    instead
    1.20
    反而
    1.18
     ainda
    1.16
    Activations Density 0.061%

    No Known Activations