© 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. 30269
    Prev
    Next
    INDEX
    Explanations

    Creates, Add, Check, Object, Credit, Create, Consistency

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

    code snippets and comments

    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
    z
    0.58
     convierte
    0.50
    ﺸ
    0.50
    ։
    0.47
    ัญลักษณ์
    0.47
     perspiciatis
    0.46
     dacă
    0.45
    اهرين
    0.45
     expresar
    0.45
     explotación
    0.45
    POSITIVE LOGITS
    ,//
    0.47
    ндай
    0.46
    弃
    0.45
    estries
    0.45
     सरकारी
    0.44
    复杂
    0.43
    crast
    0.43
    overnment
    0.42
    盛
    0.42
    oha
    0.42
    Activations Density 0.013%

    No Known Activations