© 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. 19074
    Prev
    Next
    INDEX
    Explanations

    children's performance

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

    analog circuits

    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
    Ｄ
    0.45
     etik
    0.45
     priorit
    0.44
     ATT
    0.43
     Label
    0.43
     nebude
    0.43
     FIELDS
    0.42
     Relationships
    0.41
     gelişmeler
    0.41
     instincts
    0.41
    POSITIVE LOGITS
     дет
    0.54
     зна
    0.48
    рти
    0.47
    
    0.47
     пят
    0.47
     справ
    0.46
    ۢ
    0.46
     Дет
    0.46
     подзем
    0.46
     ниже
    0.45
    Activations Density 0.000%

    No Known Activations