© 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. 22-GEMMASCOPE-2-RES-65K
    7. 641
    Prev
    Next
    INDEX
    Explanations

    teaspoon vanilla

    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
    .
    0.84
    !
    0.75
    and
    0.75
    ’
    0.73
     -
    0.71
    i
    0.71
    ..
    0.70
    ,
    0.70
    ill
    0.70
    '
    0.69
    POSITIVE LOGITS
    MovementControls
    0.84
    tpVar
    0.84
    𒅗
    0.83
    𒆪
    0.81
    𒈬
    0.81
    𒅀
    0.80
    getImageFolder
    0.79
    loadNpm
    0.79
    arrerol
    0.79
    𒊩
    0.78
    Activations Density 6.644%

    No Known Activations