© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 41-GEMMASCOPE-2-RES-65K
    4. 1422
    Prev
    Next
    INDEX
    Explanations

    conversational elements

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_width_65k_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
    ...",
    0.62
    ...',
    0.61
    ...).
    0.60
     magnetized
    0.57
    <unused62>
    0.56
    ...),
    0.56
    ...");
    0.54
     sling
    0.54
    ‐
    0.53
    aker
    0.52
    POSITIVE LOGITS
    <end_of_turn>
    2.08
    <eos>
    1.13
    ៕
    0.86
    </code>
    0.72
    ↵↵↵↵↵↵↵↵
    0.71
     继续访问
    0.70
    ↵↵↵↵↵↵↵
    0.69
    ↵↵↵↵↵↵
    0.63
    ↵↵↵↵↵
    0.60
    </html>
    0.59
    Activations Density 0.765%

    No Known Activations