Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 19102
    Prev
    Next
    INDEX
    Explanations

    principal, migration, prototype, salvation, rubber, station

    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_31_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
    ricanes
    0.60
    グ
    0.60
     perteneciente
    0.56
     is
    0.56
     włas
    0.54
     atrás
    0.52
     hermoso
    0.52
     además
    0.52
    !).
    0.52
    يط
    0.52
    POSITIVE LOGITS
    ﻟ
    0.51
    ulis
    0.50
     (
    0.48
     Irishman
    0.48
     guru
    0.48
    
    0.47
    andel
    0.46
    older
    0.46
    raft
    0.46
    Фото
    0.46
    Activations Density 0.000%

    No Known Activations