© 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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 71304
    Prev
    Next
    INDEX
    Explanations

    outcome identification or topics

    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
    akati
    0.50
    an
    0.43
    \[
    0.43
    akang
    0.43
    athi
    0.42
    well
    0.41
    ov
    0.41
    anam
    0.41
    ัก
    0.40
    kelly
    0.40
    POSITIVE LOGITS
    黼
    0.49
     ຫຼື
    0.48
     sidebar
    0.46
     Judging
    0.46
     spar
    0.46
     ور
    0.45
     ore
    0.45
     গভীরভাবে
    0.45
     Thes
    0.45
     Brief
    0.44
    Activations Density 0.013%

    No Known Activations