© 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. 17564
    Prev
    Next
    INDEX
    Explanations

    limits of

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

    complexities of relationships and anxiety

    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
    ک
    0.52
    송
    0.50
    <0x0D>
    0.49
    ن
    0.49
    (
    0.48
    You
    0.46
    м
    0.46
    ောင်း
    0.45
    ມັນ
    0.45
     accompl
    0.45
    POSITIVE LOGITS
     رجال
    0.49
     枚
    0.49
    rrbracket
    0.47
     朱
    0.47
     JULY
    0.46
    直径
    0.46
    GRESS
    0.45
     ಮೊದಲ
    0.44
    𐰇
    0.44
    اردوش
    0.44
    Activations Density 0.000%

    No Known Activations