© 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. 31-GEMMASCOPE-2-RES-262K
    7. 7572
    Prev
    Next
    INDEX
    Explanations

    sub-task descriptions

    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_31_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
    Bruno
    0.41
     Surf
    0.41
    Surf
    0.39
     experts
    0.39
    動き
    0.39
     attivo
    0.39
     सक्रिय
    0.39
    ґ
    0.39
     eth
    0.38
    Instrument
    0.38
    POSITIVE LOGITS
    ncnc
    0.51
    titleMargin
    0.44
    clubs
    0.44
    cstring
    0.43
    rawberry
    0.43
    ສາ
    0.43
    ហេ
    0.42
    calar
    0.42
    ozems
    0.42
    ଦ
    0.41
    Activations Density 0.000%

    No Known Activations