© 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. 16717
    Prev
    Next
    INDEX
    Explanations

    being the prec, media, 1, CP

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

    historical context and current state

    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
     Markets
    0.48
     League
    0.47
    ́n
    0.45
     Platforms
    0.44
     '(
    0.44
    0.44
     Stockton
    0.43
     Lehigh
    0.43
    t
    0.42
     Mortgage
    0.42
    POSITIVE LOGITS
     niektó
    0.47
     اړه
    0.46
     चर्चा
    0.45
    𝓲
    0.44
     sotto
    0.44
     مشکلات
    0.44
     کشورهای
    0.44
     épars
    0.43
     beob
    0.43
    ColorLegend
    0.43
    Activations Density 0.000%

    No Known Activations