© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138670
    Prev
    Next
    INDEX
    Explanations

    language model token limits

    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
    の種類
    0.54
    );
    0.49
    o
    0.48
    ');
    0.46
     as
    0.44
    дом
    0.44
    ())
    0.44
    ס
    0.43
    ็ม
    0.43
    แย
    0.42
    POSITIVE LOGITS
    こういう
    0.47
     parton
    0.46
     Trapez
    0.46
     पीएम
    0.46
    på
    0.44
     SDN
    0.44
     gostar
    0.43
     এরকম
    0.43
     PDT
    0.43
     Católica
    0.42
    Activations Density 0.004%

    No Known Activations