© 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. 99935
    Prev
    Next
    INDEX
    Explanations

    exposed wiring or ice

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

    Ithkuil language or similar constructed languages

    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
    خير
    0.50
     morrer
    0.46
     également
    0.46
    瀬
    0.46
    ємо
    0.45
     muslim
    0.45
    ：
    0.45
     destac
    0.43
    乖
    0.43
     mittlerweile
    0.43
    POSITIVE LOGITS
    ius
    0.44
     eius
    0.43
     etiology
    0.42
     Ecc
    0.42
    ei
    0.42
    cedures
    0.41
     lustre
    0.41
     whose
    0.41
     کاس
    0.40
     /^
    0.40
    Activations Density 0.000%

    No Known Activations