© 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. 160779
    Prev
    Next
    INDEX
    Explanations

    terms of

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

    unusual configurations or preferences

    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
     polyt
    0.49
    뉸
    0.48
     магазина
    0.48
    FromThe
    0.48
    uşt
    0.46
    管理局
    0.45
     контро
    0.44
    uggling
    0.44
     vết
    0.44
     ဗ
    0.43
    POSITIVE LOGITS
    igual
    0.46
    ципа
    0.46
    Replacement
    0.45
     Replacement
    0.43
    ூ
    0.43
     ತ
    0.42
    0.42
    Der
    0.42
    南方
    0.42
     der
    0.42
    Activations Density 0.001%

    No Known Activations