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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26901
    Prev
    Next
    INDEX
    Explanations

    parenthesized abbreviations

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

    The neuron does not respond to any of the presented text and therefore appears not to detect any particular feature.

    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
    真的是
    -1.13
    好像是
    -1.08
    They
    -1.07
    全ての
    -1.01
     überall
    -1.00
     pensamento
    -1.00
    一愣
    -0.99
     erforder
    -0.98
     mismas
    -0.95
    The
    -0.94
    POSITIVE LOGITS
     KON
    1.15
     barne
    1.12
     olie
    1.03
     zand
    1.03
     HAN
    1.01
     acero
    1.01
     zet
    0.98
    🗿
    0.97
     galeria
    0.96
    riam
    0.96
    Activations Density 0.206%

    No Known Activations