© 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. 9456
    Prev
    Next
    INDEX
    Explanations

    push back against

    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
    ro
    0.71
    acking
    0.70
     a
    0.68
    ada
    0.68
    abelle
    0.65
    anians
    0.65
    apes
    0.64
     लेकर
    0.63
    ra
    0.61
    ana
    0.61
    POSITIVE LOGITS
     for
    0.83
    ті
    0.74
    ку
    0.72
     in
    0.69
    ન
    0.63
    內
    0.61
    েল
    0.61
    ボ
    0.60
     geprüft
    0.59
    يب
    0.57
    Activations Density 0.003%

    No Known Activations