© 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. 115344
    Prev
    Next
    INDEX
    Explanations

    vocational training

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

    story points

    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
    vertices
    0.55
    STATE
    0.51
    ﮯ
    0.50
    ூரில்
    0.50
    コ
    0.49
     ocurre
    0.49
    кха
    0.49
    toxicity
    0.49
     üç
    0.48
    ⠑
    0.48
    POSITIVE LOGITS
     نوا
    0.53
     telegram
    0.46
     Read
    0.45
     Cascade
    0.40
     Set
    0.40
     Telegram
    0.40
     Hem
    0.39
    朦
    0.39
    ↵↵
    0.38
     Washing
    0.38
    Activations Density 0.000%

    No Known Activations