© 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. 137961
    Prev
    Next
    INDEX
    Explanations

    URLs with Unicode characters

    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
    k
    1.20
    i
    1.13
    '
    1.05
    B
    1.02
    P
    1.00
    J
    0.98
    g
    0.98
    K
    0.95
    ’
    0.91
    F
    0.90
    POSITIVE LOGITS
    ன்
    0.71
     τρόπο
    0.66
    ться
    0.64
     Sự
    0.64
    주시
    0.64
    ט
    0.64
    タンク
    0.63
    ání
    0.62
    ார்
    0.60
    0.60
    Activations Density 0.000%

    No Known Activations