© 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. 204852
    Prev
    Next
    INDEX
    Explanations

    goalagainforFor

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

    uses habitually or significantly

    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
    热爱
    0.49
    ό
    0.46
     পাঠ
    0.46
    ব্যাক
    0.46
    vær
    0.45
    võ
    0.45
    কোনও
    0.45
    클
    0.45
     인기
    0.44
     jakiś
    0.44
    POSITIVE LOGITS
     pry
    0.55
     effects
    0.50
     sump
    0.49
     debris
    0.49
     transformers
    0.49
     Gould
    0.48
     list
    0.48
     pistol
    0.47
     sinus
    0.47
     consequences
    0.47
    Activations Density 0.000%

    No Known Activations