© 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-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 8029
    Prev
    Next
    INDEX
    Explanations

    numbers, currencies, and years

    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_53_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
    ৮
    0.71
     ۸
    0.68
    8
    0.68
    ٨
    0.64
    ۸
    0.63
     ৮
    0.61
    ８
    0.61
    𝟖
    0.61
    <0xB9>
    0.60
    ⁸
    0.57
    POSITIVE LOGITS
    <0xB3>
    0.45
     bảy
    0.41
    <unused74>
    0.40
    大変
    0.40
    xlim
    0.39
    <0xBB>
    0.39
     Newsom
    0.39
    7
    0.38
     आप
    0.38
     seven
    0.37
    Activations Density 0.143%

    No Known Activations