© 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. 34-GEMMASCOPE-RES-131K
    7. 2718
    Prev
    Next
    INDEX
    Explanations

    step or license or click

    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
     stasiun
    -0.83
     Taking
    -0.83
     their
    -0.82
    ऩ
    -0.82
     Mischung
    -0.81
     Being
    -0.81
     considerably
    -0.79
     markedly
    -0.77
     noticeably
    -0.77
     wykonane
    -0.77
    POSITIVE LOGITS
     see
    0.99
    btnut
    0.95
     answer
    0.94
     ornate
    0.94
    γα
    0.91
    see
    0.87
    See
    0.85
    곧
    0.83
     cinq
    0.83
    くっ
    0.82
    Activations Density 0.001%

    No Known Activations