© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 29908
    Prev
    Next
    INDEX
    Explanations

    work with [

    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
     beho
    0.48
     I
    0.47
     this
    0.46
     equiv
    0.45
    displaystyle
    0.44
     ليس
    0.44
    I
    0.44
     moment
    0.43
     př
    0.43
     Scottsdale
    0.43
    POSITIVE LOGITS
    рал
    0.58
    ⨯
    0.53
    眥
    0.48
    耑
    0.47
     Emerg
    0.45
    ume
    0.45
    Editar
    0.44
    が通販できます
    0.44
    諧
    0.44
    მარ
    0.43
    Activations Density 0.000%

    No Known Activations