© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 37109
    Prev
    Next
    INDEX
    Explanations

    vector, Windows, supervised

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hunter
    0.50
    *
    0.47
    F
    0.46
    Chu
    0.45
    トリ
    0.44
    GIL
    0.44
    Meeting
    0.43
    Til
    0.43
    ēr
    0.43
    وم
    0.43
    POSITIVE LOGITS
     artific
    0.48
     букме
    0.48
     tắm
    0.46
    켠
    0.46
     mlijeka
    0.45
     б
    0.44
    ın
    0.44
    sman
    0.44
     mlij
    0.44
     fero
    0.44
    Activations Density 0.001%

    No Known Activations