© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 3639
    Prev
    Next
    INDEX
    Explanations

    acknowledges request with "okay,"

    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_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
    que
    0.78
    a
    0.68
     ord
    0.67
     ordinary
    0.66
     overheard
    0.65
    Instances
    0.64
    ać
    0.64
     ether
    0.63
     quelle
    0.63
     कि
    0.62
    POSITIVE LOGITS
    рім
    1.19
    tober
    1.12
    enação
    1.04
     Jaan
    1.04
    LAH
    1.03
    alış
    0.95
    󠁴
    0.94
    ၚ
    0.91
    ificação
    0.91
    ೇಶ
    0.91
    Activations Density 0.153%

    No Known Activations