© 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. 145353
    Prev
    Next
    INDEX
    Explanations

    days, weekends, notes

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

    dimension woven automaton

    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
    ⓓ
    0.57
    }_{+}
    0.49
    ㄗ
    0.49
    ൭
    0.48
    ൮
    0.48
    బ్ద
    0.48
    約
    0.48
    贖
    0.47
     नवम्बर
    0.47
    ਦ
    0.46
    POSITIVE LOGITS
     Rad
    0.50
    aurants
    0.49
     Ordn
    0.47
     Aufl
    0.46
     Artik
    0.46
     Dans
    0.45
     mitten
    0.44
    rad
    0.44
     auxili
    0.44
     Bajo
    0.44
    Activations Density 0.000%

    No Known Activations