© 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. 6825
    Prev
    Next
    INDEX
    Explanations

    "forward" repetition

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ac
    0.52
    实的
    0.50
    arness
    0.49
    -
    0.49
    T
    0.49
    世界的
    0.48
    ání
    0.48
    >∕
    0.48
    álu
    0.47
    gå
    0.47
    POSITIVE LOGITS
     oraz
    0.63
     sowie
    0.62
     ಹಾಗೂ
    0.58
     WIP
    0.57
     Bisby
    0.57
     relevante
    0.56
    ،
    0.56
     relevantes
    0.55
     FK
    0.55
     revistas
    0.55
    Activations Density 0.002%

    No Known Activations