© 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-65K
    7. 36349
    Prev
    Next
    INDEX
    Explanations

    input labels for queries

    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_65k_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
     &
    0.40
     Nonlinear
    0.38
     مارچ
    0.38
     charakter
    0.37
    ską
    0.37
    ivariate
    0.36
     Coding
    0.36
     करेक्ट
    0.36
     Implicit
    0.36
    accay
    0.36
    POSITIVE LOGITS
    popupIsOpen
    0.43
     hô
    0.40
     revolución
    0.39
    %@",
    0.38
    ventud
    0.37
    upon
    0.37
    ലെസ്
    0.36
    preventDefault
    0.36
     घटक
    0.36
     aéri
    0.36
    Activations Density 0.125%

    No Known Activations