© 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. 65836
    Prev
    Next
    INDEX
    Explanations

    percentages

    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
    село
    -0.89
    でございます
    -0.87
     IDisposable
    -0.87
    PAREN
    -0.84
    jewelry
    -0.83
    tote
    -0.83
    Ау
    -0.82
    ӿ
    -0.82
     RECEIVED
    -0.81
     册
    -0.81
    POSITIVE LOGITS
    әһ
    0.88
    尔的
    0.86
    ern
    0.82
     vorkommen
    0.81
    ita
    0.79
     each
    0.78
    ISD
    0.78
    son
    0.77
    lite
    0.77
    ләр
    0.76
    Activations Density 0.010%

    No Known Activations