© 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-262K
    7. 19417
    Prev
    Next
    INDEX
    Explanations

    cooking bowls and pots

    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
     latter
    0.84
     encerr
    0.82
     sonunda
    0.74
     retreated
    0.73
    런
    0.72
     shrink
    0.70
     casser
    0.69
    plicated
    0.69
     expulsion
    0.69
     প্রত্যেক
    0.68
    POSITIVE LOGITS
     Матери
    0.85
    fahrung
    0.76
     Worth
    0.76
    enziale
    0.75
     outfitted
    0.72
     Studien
    0.71
    onne
    0.70
     ஏற்ற
    0.69
    เหนือ
    0.69
    を
    0.68
    Activations Density 0.036%

    No Known Activations