© 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. 7304
    Prev
    Next
    INDEX
    Explanations

    addition of items

    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
    {
    -2.75
    *
    -2.58
    (
    -2.38
    甚至是
    -2.31
    id
    -2.25
     カットソー
    -2.22
     we
    -2.11
    妧
    -2.11
    OfWeek
    -2.09
    ',
    -2.08
    POSITIVE LOGITS
    इटम
    2.98
    觏
    2.88
    adakan
    2.73
    痦
    2.69
    What
    2.55
    铙
    2.55
    珖
    2.48
    quelize
    2.45
     Other
    2.44
    也会
    2.42
    Activations Density 0.010%

    No Known Activations