© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73137
    Prev
    Next
    INDEX
    Explanations

    each followed by verb

    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
     of
    -3.63
     it
    -2.63
     while
    -2.31
     that
    -2.30
    </u>
    -2.08
     after
    -1.88
     with
    -1.86
     at
    -1.86
     After
    -1.81
     as
    -1.77
    POSITIVE LOGITS
     piment
    1.84
    簠
    1.84
     combustível
    1.82
    賔
    1.80
    うれ
    1.80
    见识
    1.80
    溌
    1.78
     ヌード
    1.76
    抡
    1.76
    einer
    1.73
    Activations Density 0.011%

    No Known Activations