© 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. 77431
    Prev
    Next
    INDEX
    Explanations

    required by license

    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
    peg
    -0.72
    ValueChanged
    -0.69
     Теперь
    -0.68
     теперь
    -0.67
    ANNON
    -0.65
     quoique
    -0.65
    ITOS
    -0.64
     Seiko
    -0.64
    黑
    -0.63
    howto
    -0.63
    POSITIVE LOGITS
     OBITUARY
    0.75
    蜴
    0.69
    但她
    0.68
     bohater
    0.68
    опера
    0.68
    NTB
    0.67
     Keluarga
    0.66
     operativos
    0.65
     cumin
    0.65
    tructor
    0.65
    Activations Density 0.056%

    No Known Activations