© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 8132
    Prev
    Next
    INDEX
    Explanations

    programming keywords and syntax

    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_22_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
      
    0.68
    =
    0.62
     containing
    0.60
     suitable
    0.59
     extra
    0.59
    '
    0.59
    n
    0.57
     suits
    0.57
     contains
    0.56
     pf
    0.55
    POSITIVE LOGITS
    childComplexity
    0.78
    sila
    0.77
    kepsilon
    0.76
    翮
    0.75
    ᚕ
    0.74
    ⟥
    0.74
    ᚖ
    0.74
     스토리
    0.74
     ugljik
    0.73
     belladone
    0.73
    Activations Density 0.015%

    No Known Activations