© 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. 40-GEMMASCOPE-2-RES-262K
    7. 20976
    Prev
    Next
    INDEX
    Explanations

    IB related words

    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_40_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
    کش
    0.46
    Ყ
    0.45
     ㅛ
    0.43
    ifiably
    0.42
    leid
    0.42
    शे
    0.41
    fortunately
    0.41
    viol
    0.41
    contaminated
    0.40
    ށ
    0.40
    POSITIVE LOGITS
    onacci
    0.64
     kib
    0.47
     fib
    0.46
    osity
    0.45
    ্রম
    0.44
     sib
    0.44
     rib
    0.43
    rib
    0.42
     nib
    0.42
     Rib
    0.42
    Activations Density 0.019%

    No Known Activations