© 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. 1541
    Prev
    Next
    INDEX
    Explanations

    code structure terminators

    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
     মুহাম্ম
    0.29
     antifreeze
    0.27
    Neur
    0.27
    Cline
    0.27
    𒅴
    0.27
     சிந்த
    0.26
     باپ
    0.26
    usions
    0.26
     облег
    0.26
     brachial
    0.26
    POSITIVE LOGITS
     financi
    0.30
    将会
    0.29
     ଦ
    0.29
    ’
    0.29
    ().
    0.28
     revenue
    0.28
     won
    0.27
     osób
    0.27
     以及
    0.27
    により
    0.27
    Activations Density 0.479%

    No Known Activations