© 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. 44097
    Prev
    Next
    INDEX
    Explanations

    seventy followed by a number

    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
    ୈ
    -3.13
     Which
    -2.94
    g
    -2.84
    which
    -2.66
     then
    -2.63
    “
    -2.55
    鰾
    -2.53
    璨
    -2.45
    栒
    -2.38
    a
    -2.36
    POSITIVE LOGITS
    "
    2.69
     Détails
    2.61
    Ouverture
    2.50
    🔸
    2.48
     rumbling
    2.39
     thump
    2.36
     ouverture
    2.36
     évaluation
    2.33
    ſu
    2.31
    ſelf
    2.30
    Activations Density 0.005%

    No Known Activations