© 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. 37172
    Prev
    Next
    INDEX
    Explanations

    reward, kiosk, crispy, HC, days

    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
    ิ
    0.54
    ナナ
    0.50
     aux
    0.50
    س
    0.49
    バージョン
    0.48
    ер
    0.48
     navegar
    0.47
     i
    0.47
     recru
    0.47
     efficiencies
    0.46
    POSITIVE LOGITS
    Order
    0.51
    शील
    0.44
    State
    0.43
    Common
    0.42
    Hamilton
    0.42
    isComposite
    0.41
     griech
    0.41
    Loss
    0.41
    (
    0.41
    Handling
    0.40
    Activations Density 0.001%

    No Known Activations