© 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. 98158
    Prev
    Next
    INDEX
    Explanations

    code elements and dialogue

    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
     nomin
    -0.90
    џ
    -0.88
     to
    -0.86
    指南
    -0.86
    з
    -0.85
     recognizable
    -0.84
     darstellen
    -0.84
    цо
    -0.83
    const
    -0.82
    ัด
    -0.82
    POSITIVE LOGITS
    haped
    1.06
    siya
    0.97
     membag
    0.93
    tothe
    0.90
     Два
    0.90
    aried
    0.84
    cand
    0.84
    рії
    0.84
    Boat
    0.82
    told
    0.81
    Activations Density 0.022%

    No Known Activations