© 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. 25228
    Prev
    Next
    INDEX
    Explanations

    explaining history and harm

    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
     펼
    0.46
    ；
    0.46
     anchors
    0.44
     expanded
    0.44
    știg
    0.44
     acidified
    0.43
     ९
    0.43
    avacanam
    0.43
     antler
    0.42
    $.;
    0.42
    POSITIVE LOGITS
    媤
    0.53
    叓
    0.50
     nostre
    0.44
     köszön
    0.44
     Huy
    0.43
    ورية
    0.42
    슨
    0.41
    اط
    0.41
    ուր
    0.40
    有害
    0.40
    Activations Density 0.001%

    No Known Activations