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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 43802
    Prev
    Next
    INDEX
    Explanations

    spray the most

    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
    یی
    0.57
    at
    0.53
     وبعد
    0.53
     ت
    0.48
    ngthen
    0.47
    Create
    0.45
    非常
    0.45
    만큼
    0.45
    زان
    0.44
     Children
    0.43
    POSITIVE LOGITS
     вулка
    0.53
     piante
    0.48
    蚜
    0.47
    פל
    0.47
     conifers
    0.47
     grasses
    0.45
     thermoelectric
    0.45
    気軽に
    0.45
     રી
    0.45
     phonons
    0.45
    Activations Density 0.000%

    No Known Activations