© 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. 65272
    Prev
    Next
    INDEX
    Explanations

    GPs after comma

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

    ranking or scale

    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
    loadConst
    0.43
    反复
    0.43
    getDeclared
    0.42
    コンサート
    0.42
    に至
    0.40
    certain
    0.40
     নিশ্চয়
    0.40
    
    0.39
    |");
    0.39
    jeć
    0.39
    POSITIVE LOGITS
     melanin
    0.50
     trainees
    0.49
     fortuit
    0.49
     shifting
    0.49
     trainee
    0.48
     switching
    0.48
     broadening
    0.48
     fokus
    0.48
     coprodu
    0.48
     braiding
    0.47
    Activations Density 0.000%

    No Known Activations