© 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. 57361
    Prev
    Next
    INDEX
    Explanations

    organization, union, and program context

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

    defining requirements and strategy

    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
    ຈາກ
    0.54
     仕
    0.54
    gelijk
    0.53
     металла
    0.52
     思っ
    0.52
    osilicate
    0.52
    |+\
    0.51
    ligence
    0.50
     同じ
    0.50
     आस्ट्रेलिया
    0.50
    POSITIVE LOGITS
     program
    0.52
     programme
    0.48
    م
    0.48
     contact
    0.45
     v
    0.44
    am
    0.44
     show
    0.44
     Call
    0.44
     PROGRAM
    0.44
     Rich
    0.44
    Activations Density 0.000%

    No Known Activations