© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72715
    Prev
    Next
    INDEX
    Explanations

    a.k.a or initials

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

    The neuron strongly fires on isolated single-letter alphabetic tokens (e.g. lone “k,” “x,” “G,” “R,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     Of
    -2.64
    鹮
    -2.39
     However
    -2.23
     While
    -2.14
    乆
    -2.11
    Pgina
    -2.09
    ?"
    -2.06
    嚒
    -2.06
     Many
    -2.05
    زارش
    -2.02
    POSITIVE LOGITS
    In
    3.28
    }
    2.77
     myriad
    2.72
    ?
    2.66
    “…
    2.44
    O
    2.31
    “[
    2.30
    --
    2.30
    [
    2.22
    D
    2.20
    Activations Density 0.059%

    No Known Activations