© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12504
    Prev
    Next
    INDEX
    Explanations

    execute code, scripts, methods

    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_22/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
    に行く
    -2.88
    '
    -2.56
    Y
    -2.38
    J
    -2.34
    C
    -2.31
    e
    -2.30
    遢
    -2.25
    ῞
    -2.22
    ’
    -2.19
     {
    -2.13
    POSITIVE LOGITS
    ୈ
    3.56
    沇
    2.72
    ಞ
    2.53
    噚
    2.52
    彣
    2.45
    我们
    2.44
    ⤞
    2.38
    で
    2.30
    灕
    2.30
     手作り
    2.28
    Activations Density 0.020%

    No Known Activations