© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 10520
    Prev
    Next
    INDEX
    Explanations

    books by authors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
     v
    1.16
     r
    1.15
     Sem
    1.06
     TextStyle
    1.03
     Pd
    1.01
     τα
    1.00
     גם
    0.99
     How
    0.98
     colors
    0.98
     ל
    0.97
    POSITIVE LOGITS
    Various
    1.06
    Terry
    0.95
     manusia
    0.90
     diffus
    0.87
    Editors
    0.85
    Staff
    0.83
    <unused1685>
    0.82
    liz
    0.82
     afront
    0.81
    NA
    0.81
    Activations Density 0.001%

    No Known Activations