© 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. 243302
    Prev
    Next
    INDEX
    Explanations

    budget

    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
    as
    0.52
    ar
    0.50
    en
    0.50
    am
    0.46
    oja
    0.45
    苦
    0.45
    em
    0.44
    ்க்க
    0.44
     विवेक
    0.44
     peacetime
    0.44
    POSITIVE LOGITS
    onders
    0.49
    
    0.43
    ত্র
    0.42
     imput
    0.42
    丂
    0.42
    িন্দু
    0.42
    SCHEDULE
    0.42
     以及
    0.42
    Iteration
    0.41
     aar
    0.41
    Activations Density 0.000%

    No Known Activations