© 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. 31890
    Prev
    Next
    INDEX
    Explanations

    save for later or money

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

    save the code

    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
    ]");
    0.60
    はん
    0.59
    s
    0.54
    SKI
    0.50
    गंध
    0.49
    お手
    0.49
    Deux
    0.49
    は
    0.48
    ों
    0.48
    হা
    0.48
    POSITIVE LOGITS
     saves
    1.11
     save
    1.10
     Save
    1.06
     saving
    1.05
     保存
    1.02
    save
    0.97
     SAVE
    0.96
     Saving
    0.95
    saving
    0.94
     Saves
    0.87
    Activations Density 0.078%

    No Known Activations