© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49667
    Prev
    Next
    INDEX
    Explanations

    time stamps or specific phrases endings

    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_34/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
     Magen
    -0.89
     Compatibility
    -0.75
     alibi
    -0.75
     compatibility
    -0.74
     VICTORIA
    -0.72
    Compati
    -0.71
     compat
    -0.69
     लोग
    -0.69
    Limiter
    -0.68
     Balm
    -0.67
    POSITIVE LOGITS
     BT
    0.88
    jede
    0.84
    ฝ
    0.79
     bebé
    0.79
    strand
    0.78
    ɖ
    0.78
    anho
    0.77
    環境
    0.77
    Death
    0.75
    ámetro
    0.75
    Activations Density 0.005%

    No Known Activations