© 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. 16-GEMMASCOPE-2-RES-262K
    7. 11471
    Prev
    Next
    INDEX
    Explanations

    danger, specific, whether

    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_16_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
    ;
    0.57
    namely
    0.48
     finition
    0.47
    phere
    0.47
    boleh
    0.46
     equiv
    0.45
    key
    0.45
    ấ
    0.45
     dimensions
    0.45
     kunna
    0.44
    POSITIVE LOGITS
    arcie
    0.47
    ेर
    0.47
    ünüz
    0.46
    ários
    0.46
    enzi
    0.45
    ancake
    0.45
    ész
    0.45
    asă
    0.45
    eni
    0.44
    กระ
    0.43
    Activations Density 0.000%

    No Known Activations