© 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. 45275
    Prev
    Next
    INDEX
    Explanations

    Translate, Install, CHORUS, Justin

    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
    tvguide
    -1.62
    layah
    -1.55
    YNAMIC
    -1.55
     and
    -1.55
     cuyos
    -1.52
    tapis
    -1.47
    utusan
    -1.46
    crites
    -1.46
    indari
    -1.45
     ਅਤੇ
    -1.45
    POSITIVE LOGITS
    ,
    1.68
    l
    1.59
    其他
    1.59
    ah
    1.59
    re
    1.57
    1
    1.55
    ko
    1.50
    9
    1.50
    ve
    1.50
    6
    1.48
    Activations Density 0.035%

    No Known Activations