© 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. 238713
    Prev
    Next
    INDEX
    Explanations

    Lord of hosts; sections; channel; all; played; together

    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
     MAINTENANCE
    0.43
     INSPE
    0.43
     QUESTION
    0.42
     計算
    0.42
    ⁸
    0.42
    \,
    0.41
     MONTH
    0.41
     தொடர்பான
    0.41
     रा
    0.41
    ~(
    0.41
    POSITIVE LOGITS
     انہوں
    0.47
    ництво
    0.46
    न्होंने
    0.46
     Gründung
    0.44
     iniciativa
    0.43
    indruck
    0.43
     Olsen
    0.43
    控股
    0.42
     creatividad
    0.42
    Heute
    0.42
    Activations Density 0.002%

    No Known Activations