© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 51035
    Prev
    Next
    INDEX
    Explanations

    decide, Expansion, Part ID

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    敵人
    0.56
    ুনে
    0.51
     ഇന്ത്യൻ
    0.47
    étaient
    0.47
     врача
    0.46
    𝗵
    0.46
    કો
    0.46
     বিখ্যাত
    0.46
     ordinairement
    0.45
     ዓይነት
    0.45
    POSITIVE LOGITS
     munic
    0.41
     
    0.40
    领先
    0.39
     nodig
    0.38
     lilac
    0.38
     beak
    0.38
    <0x95>
    0.37
    ./
    0.37
     hanya
    0.37
     shr
    0.37
    Activations Density 0.002%

    No Known Activations