© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 57798
    Prev
    Next
    INDEX
    Explanations

    ingredients and form of

    np_acts-logits-general · gemini-2.5-flash-lite

    sources where capabilities arise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     administrat
    0.47
    ,/*
    0.44
     bezpiecze
    0.42
     signal
    0.41
     uncertainty
    0.41
     miserable
    0.41
     boilerplate
    0.40
     Gospod
    0.40
     Gianni
    0.39
     artificially
    0.39
    POSITIVE LOGITS
    ।
    0.59
     убор
    0.55
    انی
    0.54
    keen
    0.54
     کا
    0.53
     फोर्
    0.51
     کو
    0.50
     بھائی
    0.49
     پور
    0.48
    ։
    0.47
    Activations Density 0.000%

    No Known Activations