© 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. 59383
    Prev
    Next
    INDEX
    Explanations

    publishing actions

    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
    姈
    -2.70
    ikusbot
    -2.58
    鹋
    -2.53
    翃
    -2.47
     of
    -2.45
    弍
    -2.36
    殽
    -2.28
    玊
    -2.27
     tetapi
    -2.25
    輅
    -2.25
    POSITIVE LOGITS
    {
    3.17
    c
    3.03
    勠
    2.97
    ementara
    2.67
    不会
    2.61
    镦
    2.55
    的
    2.50
    是
    2.45
    ⡯
    2.44
    他
    2.42
    Activations Density 0.005%

    No Known Activations