© 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. 107154
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical terms

    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
     have
    -0.76
    chargez
    -0.74
     only
    -0.71
    -@
    -0.71
     Хе
    -0.71
    ölt
    -0.70
     statut
    -0.69
    简介
    -0.69
    пени
    -0.69
     早餐
    -0.69
    POSITIVE LOGITS
     μέχρι
    0.91
     матч
    0.87
     miếng
    0.83
     Pim
    0.82
    Understand
    0.81
     MIGHT
    0.81
    üben
    0.80
     προς
    0.80
     Ctrl
    0.79
     \%$
    0.79
    Activations Density 0.002%

    No Known Activations