© 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. 45169
    Prev
    Next
    INDEX
    Explanations

    possum, possession, possible, proprioception

    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
    髡
    -3.13
    攆
    -2.59
    箆
    -2.58
    selbe
    -2.55
    猡
    -2.53
    鈊
    -2.53
    辔
    -2.52
    Febru
    -2.42
     Chriftian
    -2.41
     konkrete
    -2.38
    POSITIVE LOGITS
    {
    3.13
     There
    2.66
    n
    2.52
     Historically
    2.42
     Furthermore
    2.33
     nurturing
    2.31
     Conversely
    2.31
     Regarding
    2.30
    s
    2.27
     Есть
    2.22
    Activations Density 0.003%

    No Known Activations