Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 11486
    Prev
    Next
    INDEX
    Explanations

    describing components or aspects

    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
    。」
    0.30
    ۔
    0.29
    》。
    0.29
    。
    0.28
     ۔
    0.28
    返す
    0.28
    耸
    0.28
    说道
    0.28
     ។
    0.28
    这里的
    0.27
    POSITIVE LOGITS
     husbandry
    0.28
    мель
    0.27
     with
    0.26
     complexity
    0.26
     okun
    0.26
    ventura
    0.25
     foray
    0.25
     amoureux
    0.25
     adjudication
    0.25
     comprised
    0.25
    Activations Density 0.154%

    No Known Activations