© 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. 197016
    Prev
    Next
    INDEX
    Explanations

    penalties and inspections

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

    character and profiles

    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
    TOOL
    0.55
    早上
    0.51
     совместно
    0.51
    туи
    0.51
    kében
    0.51
    𝙄
    0.51
    䨘
    0.50
     осна
    0.50
    TISE
    0.50
     спів
    0.50
    POSITIVE LOGITS
     inspectors
    0.51
     penalties
    0.48
    ↵↵↵
    0.45
     inspections
    0.45
     care
    0.44
     inquiries
    0.44
    nThe
    0.44
    ating
    0.43
     careful
    0.43
     enquiries
    0.43
    Activations Density 0.001%

    No Known Activations