© 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. 15800
    Prev
    Next
    INDEX
    Explanations

    events, stable, foundation

    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
     दोन
    0.41
    คน
    0.40
    𢎞
    0.39
     بابەت
    0.39
    เจ
    0.38
     வேண்ட
    0.38
     横
    0.38
     존
    0.37
    目光
    0.37
    Mip
    0.37
    POSITIVE LOGITS
    ീസ്
    0.42
     again
    0.40
     excellently
    0.40
     dharm
    0.38
     excelled
    0.38
     hours
    0.38
     RCC
    0.38
    ers
    0.37
    дяки
    0.37
     আল্লাহর
    0.37
    Activations Density 0.009%

    No Known Activations