© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 208200
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite

    renders or broken

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </sub>
    0.47
    riya
    0.45
     کشورهای
    0.42
     हुए
    0.42
     நாளை
    0.40
     சினிம
    0.39
     디자인
    0.39
     reales
    0.39
    odi
    0.39
    usus
    0.39
    POSITIVE LOGITS
    ғы
    0.46
    ɧ
    0.46
    LockButton
    0.46
    中年
    0.46
    Vai
    0.46
    вих
    0.44
    慎
    0.43
     vai
    0.43
    蘞
    0.43
     mutton
    0.42
    Activations Density 0.002%

    No Known Activations