© 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. 17365
    Prev
    Next
    INDEX
    Explanations

    website footer component

    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
    ل
    0.94
    _
    0.86
    ق
    0.86
    '
    0.86
    هم
    0.82
    ه
    0.82
    2
    0.81
    bouw
    0.79
    ।
    0.78
    𝟏
    0.77
    POSITIVE LOGITS
     are
    0.74
    in
    0.70
    os
    0.69
    ла
    0.68
    at
    0.66
    as
    0.66
    ICK
    0.66
     footer
    0.65
    or
    0.64
     filosofia
    0.63
    Activations Density 0.001%

    No Known Activations