© 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. 213340
    Prev
    Next
    INDEX
    Explanations

    specifying subsequent items

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

    variation, difference, change

    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
    Negative Logits
     Respublik
    0.54
     उत्सर्जन
    0.50
    oxylated
    0.49
     แบ่ง
    0.47
     বিভক্ত
    0.47
    oxycholic
    0.47
     Southwestern
    0.47
     divided
    0.46
     Mets
    0.46
    ǧ
    0.46
    POSITIVE LOGITS
    ",
    0.47
     prijs
    0.45
    .",
    0.44
     बाद
    0.44
    ",$
    0.43
     similares
    0.40
     cosas
    0.40
    .',
    0.40
     populaires
    0.40
     iba
    0.39
    Activations Density 0.001%

    No Known Activations