© 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. 59299
    Prev
    Next
    INDEX
    Explanations

    in followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     the
    -2.84
    に
    -2.08
    by
    -2.02
    N
    -1.93
    as
    -1.93
    to
    -1.85
    and
    -1.80
    <td>
    -1.77
    le
    -1.75
    :
    -1.73
    POSITIVE LOGITS
    尨
    2.25
    𖧵
    2.11
    ௅
    1.80
    ⽼
    1.80
     Sementara
    1.80
    櫺
    1.80
     بينما
    1.77
    titial
    1.77
    媪
    1.77
    źć
    1.77
    Activations Density 0.040%

    No Known Activations