© 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. 29804
    Prev
    Next
    INDEX
    Explanations

    save money, tools, equipment

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

    invisible ink

    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
    Pak
    0.44
    STE
    0.43
    лені
    0.43
     Paese
    0.42
    лли
    0.42
    uttab
    0.42
    ミ
    0.42
    プロ
    0.42
    lije
    0.41
    MER
    0.41
    POSITIVE LOGITS
     Epidemiology
    0.53
    épid
    0.53
     एपिस
    0.51
    ၻ
    0.50
     ञ
    0.49
    械
    0.49
    ggplot
    0.48
    ০১
    0.48
     Divid
    0.48
    键盘
    0.47
    Activations Density 0.001%

    No Known Activations