© 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. 169908
    Prev
    Next
    INDEX
    Explanations

    specific details and exceptions

    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
    owaną
    0.48
     ===========
    0.48
    ́p
    0.47
    演员
    0.47
    owany
    0.47
     chub
    0.47
    δια
    0.46
    ས་
    0.46
    کنندگان
    0.45
    ＝＝
    0.45
    POSITIVE LOGITS
     combining
    0.48
     tack
    0.47
    ↵↵
    0.46
     that
    0.46
     obt
    0.45
     applying
    0.45
    -
    0.45
     oxidative
    0.44
     I
    0.44
     using
    0.44
    Activations Density 0.005%

    No Known Activations