© 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. 18023
    Prev
    Next
    INDEX
    Explanations

    std::unordered_map, Boothill, tonsil, ax

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

    accounting for

    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
    쇤
    0.48
    σμ
    0.42
    γεν
    0.42
    숑
    0.42
    일
    0.41
    created
    0.41
     zus
    0.41
    
    0.40
    Ꮄ
    0.40
    이제
    0.40
    POSITIVE LOGITS
     ఎన్ని
    0.49
     relentless
    0.46
     unrelenting
    0.45
     Setup
    0.42
    ových
    0.41
     Screenshots
    0.41
     difficiles
    0.41
     Management
    0.41
     Rules
    0.41
     (\
    0.40
    Activations Density 0.000%

    No Known Activations