© 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. 22-GEMMASCOPE-RES-131K
    7. 65410
    Prev
    Next
    INDEX
    Explanations

    existing or previous states

    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
     senare
    -0.97
    ómicos
    -0.81
     新增
    -0.79
    完成です
    -0.75
     Later
    -0.75
     GHS
    -0.73
    ктория
    -0.73
    uksia
    -0.73
    vereign
    -0.71
     ahora
    -0.69
    POSITIVE LOGITS
     already
    2.77
    already
    2.19
     existing
    2.19
    Already
    2.14
     уже
    2.08
     previous
    1.89
     bereits
    1.88
     Already
    1.88
     previously
    1.82
     вже
    1.75
    Activations Density 0.089%

    No Known Activations