© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 9416
    Prev
    Next
    INDEX
    Explanations

    higher-order statistics and frequency components

    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_16_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
     A
    0.68
     T
    0.61
    1
    0.58
     Every
    0.55
     There
    0.55
     engen
    0.54
     Aztecs
    0.54
     ещё
    0.53
     Evers
    0.53
     are
    0.52
    POSITIVE LOGITS
    ૨
    0.61
    ﺍ
    0.60
    ン
    0.58
    Ι
    0.58
    ﻥ
    0.56
    בית
    0.56
    Ⲃ
    0.54
    nergie
    0.54
     energije
    0.52
    ꗥ
    0.52
    Activations Density 0.035%

    No Known Activations