© 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. 41900
    Prev
    Next
    INDEX
    Explanations

    looking for or at

    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
    想
    0.43
    Tou
    0.40
    煩
    0.39
    ຝ
    0.39
     PLANNING
    0.38
     ವಿಷಯ
    0.38
     દ્વા
    0.38
    ン
    0.37
    ಯೋಗ
    0.37
     vented
    0.36
    POSITIVE LOGITS
     πέ
    0.42
    fireFlower
    0.41
    dSample
    0.38
    棰
    0.38
    kepsilon
    0.37
    bikes
    0.37
    忻
    0.36
     î
    0.36
    avacanam
    0.36
     ადამიან
    0.36
    Activations Density 0.001%

    No Known Activations