© 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. 26043
    Prev
    Next
    INDEX
    Explanations

    possessive 's

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

    defining characteristics

    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
     kontinuier
    0.45
    statements
    0.40
    葛
    0.38
     fuelled
    0.37
     motivated
    0.36
    ィ
    0.35
    Agg
    0.35
     varía
    0.35
     ispir
    0.35
     sämt
    0.34
    POSITIVE LOGITS
    门口
    0.49
    还没有
    0.49
     зда
    0.46
     เจ้า
    0.46
     Chưa
    0.46
     lui
    0.43
     ใบ
    0.43
     紙
    0.43
     сега
    0.43
     Şubat
    0.42
    Activations Density 0.000%

    No Known Activations