© 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. 168058
    Prev
    Next
    INDEX
    Explanations

    craftsmanship and artistic skill

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

    language diversity

    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
    <0x0D>
    0.51
     CMD
    0.46
    ഋ
    0.45
     pente
    0.44
     எம்
    0.43
    妗
    0.42
     verstehen
    0.42
     perceived
    0.42
     craft
    0.42
    元年
    0.41
    POSITIVE LOGITS
    urers
    0.55
    ಾಗಿದೆ
    0.50
    limit
    0.48
    uing
    0.46
    ق
    0.45
    atios
    0.45
    resso
    0.45
    ясплат
    0.45
    nolds
    0.43
    opolitan
    0.43
    Activations Density 0.000%

    No Known Activations