© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 935
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
    uestra
    0.32
    싶
    0.30
     usare
    0.30
    leda
    0.30
    적이
    0.30
     thermodynam
    0.29
    比如说
    0.29
    🥓
    0.29
     acus
    0.29
     cria
    0.29
    POSITIVE LOGITS
    峨
    0.25
     ١
    0.25
    荽
    0.24
    5
    0.24
    డ్‌
    0.23
    2
    0.23
    3
    0.23
    玥
    0.23
     skills
    0.23
     errorMessage
    0.23
    Activations Density 0.000%

    No Known Activations