© 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. 35857
    Prev
    Next
    INDEX
    Explanations

    time stamps and durations

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

    models response

    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
    Memory
    0.40
     dicion
    0.40
     liggen
    0.39
     เม
    0.38
     列
    0.38
     เข
    0.38
     flexibilidad
    0.38
     Enumer
    0.38
     šk
    0.38
     udział
    0.38
    POSITIVE LOGITS
    ellae
    0.37
     cursed
    0.36
    эр
    0.36
     grotesque
    0.35
    ỏ
    0.35
     fireplace
    0.35
     domestically
    0.34
    radar
    0.34
    मेंट्स
    0.34
     radar
    0.33
    Activations Density 0.013%

    No Known Activations