© 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. 31042
    Prev
    Next
    INDEX
    Explanations

    research methods

    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
     Jugendliche
    -0.76
     begyn
    -0.75
    Only
    -0.75
     only
    -0.73
    kenzo
    -0.69
     cafes
    -0.69
    ｫ
    -0.69
     Estimated
    -0.69
     Pl
    -0.68
    qualification
    -0.68
    POSITIVE LOGITS
    ształ
    0.79
     ihn
    0.78
    udz
    0.78
    REFERRED
    0.78
     Entropy
    0.77
     Cyclone
    0.76
    skem
    0.76
    レビュー
    0.76
    zyka
    0.76
    showError
    0.75
    Activations Density 0.109%

    No Known Activations