© 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. 36270
    Prev
    Next
    INDEX
    Explanations

    numbers

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

    dictators, rental, worst, best

    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
    Fra
    0.55
    פ
    0.54
    Impossible
    0.53
    п
    0.52
    Angel
    0.51
    Ub
    0.50
    Laut
    0.50
    Instagram
    0.48
    Avatar
    0.48
    Stefan
    0.48
    POSITIVE LOGITS
     databases
    0.49
     tabulation
    0.48
     Databases
    0.46
     "-",
    0.45
     hasattr
    0.45
     CONTRIBUT
    0.45
     diagnostics
    0.44
     ;{
    0.44
     concernant
    0.44
     enhances
    0.43
    Activations Density 0.000%

    No Known Activations