© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 5389
    Prev
    Next
    INDEX
    Explanations

    code constructs and operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     commander
    0.53
     robuste
    0.53
    叁章
    0.53
    <unused1840>
    0.53
     esencial
    0.52
    መም
    0.51
     dSample
    0.51
     auch
    0.51
     veniam
    0.51
     Gelegenheit
    0.51
    POSITIVE LOGITS
    [
    0.91
    [-
    0.76
    ()[
    0.70
    \[
    0.70
    Variable
    0.67
    variable
    0.67
    VariableName
    0.65
    ToString
    0.65
    [(
    0.64
     variable
    0.64
    Activations Density 0.101%

    No Known Activations