© 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. 123848
    Prev
    Next
    INDEX
    Explanations

    explaining function definitions

    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
    </h6>
    0.54
    .
    0.47
     pól
    0.46
    。
    0.44
     位置
    0.44
     усилия
    0.44
     направления
    0.43
    io
    0.43
     склад
    0.42
     Liang
    0.42
    POSITIVE LOGITS
    patient
    0.48
    Remote
    0.47
    癲
    0.46
    vič
    0.45
     multicol
    0.45
    actively
    0.45
    EV
    0.44
    bidden
    0.43
    pesas
    0.43
    ❮
    0.43
    Activations Density 0.001%

    No Known Activations