© 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. 133542
    Prev
    Next
    INDEX
    Explanations

    subjective opinions

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

    no personal opinions

    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
     पीड़
    0.57
     бір
    0.57
     옆
    0.55
     бир
    0.54
     જાણ
    0.53
    ő
    0.53
     хочет
    0.52
     홈
    0.52
     ጊዜ
    0.52
     됐
    0.52
    POSITIVE LOGITS
     I
    0.50
     Cerv
    0.45
     Ach
    0.45
    سين
    0.45
     Pari
    0.44
     El
    0.44
     Az
    0.43
     Muscle
    0.43
     CRI
    0.43
     OMC
    0.43
    Activations Density 0.000%

    No Known Activations