© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 149600
    Prev
    Next
    INDEX
    Explanations

    document category fields

    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_29_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
     ("
    1.29
     ($
    1.25
     (
    1.21
     ('
    1.19
     (“
    1.18
     (-
    1.14
     reduces
    1.13
     (+
    1.11
     ([
    1.11
     (!
    1.08
    POSITIVE LOGITS
    бие
    0.84
     }}$,
    0.82
    AsyncKeyState
    0.79
     mixto
    0.78
     LPARAM
    0.76
    дом
    0.76
    Lunar
    0.71
    Ма
    0.71
    ),]),
    0.71
    osphère
    0.71
    Activations Density 0.052%

    No Known Activations