© 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. 4502
    Prev
    Next
    INDEX
    Explanations

    multi-component or multi-stage descriptions

    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
    ość
    0.39
    ları
    0.39
    ه‌ها
    0.39
    न
    0.36
    こと
    0.36
    larına
    0.36
    ⤒
    0.35
     grunds
    0.35
     fenomeni
    0.35
    IZATION
    0.35
    POSITIVE LOGITS
    umed
    0.32
    <0x80>
    0.30
    принима
    0.30
    \"
    0.29
     completes
    0.29
     linestyle
    0.29
     lossless
    0.29
     pedestrian
    0.28
     continuous
    0.28
     unwavering
    0.28
    Activations Density 0.005%

    No Known Activations