© 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. 10340
    Prev
    Next
    INDEX
    Explanations

    COMPLEMENT / :: / .parents

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

    programming, exchange, schema, application

    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
     -&
    0.38
    örungen
    0.38
     Travers
    0.37
     amounted
    0.36
     occurred
    0.36
    worthiness
    0.36
     Groundwater
    0.36
     underwent
    0.36
    ubercul
    0.36
     attenu
    0.35
    POSITIVE LOGITS
    Arquivo
    0.55
    getFull
    0.46
     diversify
    0.44
    મ
    0.43
     manipulate
    0.43
    Compute
    0.42
    र्टी
    0.42
     क्रिएट
    0.42
    社區
    0.42
    زن
    0.41
    Activations Density 0.000%

    No Known Activations