© 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. 40-GEMMASCOPE-2-RES-262K
    4. 4503
    Prev
    Next
    INDEX
    Explanations

    symbols and separators

    np_acts-logits-general · gemini-2.5-flash-lite

    numeric literals, especially floating-point values (e.g., coordinates, measurements, IDs) within technical or code-like contexts

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    Strafpunkte
    0.18
    udarstven
    0.17
    elwv
    0.17
    ClearedBy
    0.17
    ArtStudent
    0.16
    <unused543>
    0.16
    XSSFSheet
    0.16
    Despatx
    0.15
    }+...+\
    0.15
    ຽ
    0.15
    POSITIVE LOGITS
    ↵↵
    0.18
    ↵
    0.18
      
    0.17
     ,
    0.16
     while
    0.16
     and
    0.16
    <h2>
    0.16
     making
    0.16
    In
    0.15
    And
    0.15
    Activations Density 0.447%

    No Known Activations