© 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. 224607
    Prev
    Next
    INDEX
    Explanations

    hardware mounting

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

    emotion and conversion

    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
     взгля
    0.46
    衡
    0.43
     writeFile
    0.43
     iterate
    0.43
    ILA
    0.42
    岑
    0.42
    िसोदिया
    0.42
     бере
    0.42
    мони
    0.41
    宥
    0.41
    POSITIVE LOGITS
     veilig
    0.50
    غير
    0.49
    ggbb
    0.48
     excelente
    0.45
     perfecta
    0.45
     alá
    0.43
     blitt
    0.43
    üp
    0.43
    cum
    0.42
     multival
    0.42
    Activations Density 0.002%

    No Known Activations