© 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. 58961
    Prev
    Next
    INDEX
    Explanations

    names following Mrs

    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
    俅
    -2.25
    ၟ
    -2.17
    ༴
    -2.16
    蟜
    -2.02
     Pokud
    -2.02
    ſu
    -1.98
    戗
    -1.93
    ayangkan
    -1.92
    sprzed
    -1.91
     alongside
    -1.90
    POSITIVE LOGITS
    and
    2.75
    i
    2.61
    s
    2.56
    b
    2.55
    of
    2.34
    有不
    2.34
    a
    2.31
    o
    2.25
    It
    2.13
    <i>
    2.06
    Activations Density 0.003%

    No Known Activations