© 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. 128018
    Prev
    Next
    INDEX
    Explanations

    describing accompanying elements or characteristics

    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
     også
    -1.60
    ah
    -1.60
    ?”
    -1.59
    ”.
    -1.58
     też
    -1.55
    .
    -1.54
    for
    -1.53
    ↵
    -1.52
    媄
    -1.49
    .'”
    -1.43
    POSITIVE LOGITS
    儅
    2.22
    蹀
    1.79
    🫓
    1.74
    టి
    1.73
    cinnamon
    1.66
     such
    1.65
    珹
    1.65
    鉏
    1.64
     philosophie
    1.63
    iſter
    1.62
    Activations Density 0.062%

    No Known Activations