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. 9335
    Prev
    Next
    INDEX
    Explanations

    connecting nodes data

    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
     wodurch
    0.30
     Необходимо
    0.28
    뷊
    0.27
     コンパクト
    0.27
     சுற்றுச்சூழ
    0.27
    чиго
    0.26
     Таким
    0.26
     సహాయ
    0.26
     ተግባ
    0.26
     Sehingga
    0.25
    POSITIVE LOGITS
    /
    0.32
     (
    0.29
     at
    0.29
     with
    0.28
    -
    0.28
     and
    0.27
     from
    0.27
     if
    0.26
     of
    0.26
     or
    0.26
    Activations Density 0.611%

    No Known Activations