© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 59295
    Prev
    Next
    INDEX
    Explanations

    names, places, or tests

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

    medical or problem outcomes

    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
     routing
    0.52
    Through
    0.50
    Routing
    0.48
    QUA
    0.47
     comes
    0.44
    দ্ভ
    0.44
    랑
    0.44
     znač
    0.43
    CY
    0.43
     mariage
    0.43
    POSITIVE LOGITS
     २
    0.50
    ppure
    0.46
    typescript
    0.44
     отме
    0.43
     Hayashi
    0.41
     outsiders
    0.40
    dol
    0.40
     Wiesner
    0.40
    黯
    0.40
     सूरज
    0.39
    Activations Density 0.000%

    No Known Activations