© 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
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 45779
    Prev
    Next
    INDEX
    Explanations

    request leave or time

    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_16_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
    ↵↵
    0.89
    ли
    0.78
    quele
    0.66
    กก
    0.66
     मद्देन
    0.65
    いろんな
    0.65
    live
    0.62
    দের
    0.62
    ರ
    0.62
    focused
    0.61
    POSITIVE LOGITS
     для
    0.67
     données
    0.66
    נות
    0.61
    ॉन
    0.60
    <0x1D>
    0.59
    ையம்
    0.59
     цены
    0.59
    اني
    0.58
     to
    0.58
    Attribute
    0.58
    Activations Density 0.000%

    No Known Activations