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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 5112
    Prev
    Next
    INDEX
    Explanations

    lists with colons

    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_65k_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
    (
    0.27
     }(
    0.26
    ﹙
    0.25
     Andrade
    0.25
     های
    0.23
     విధాన
    0.23
     $(
    0.23
     版本
    0.23
     (
    0.23
    IZ
    0.23
    POSITIVE LOGITS
    TreeClassifier
    0.23
     사람이
    0.23
    azał
    0.22
     قَالَ
    0.22
     weren
    0.22
    媢
    0.21
     relatable
    0.21
    さまざ
    0.21
    چے
    0.21
     galore
    0.21
    Activations Density 0.332%

    No Known Activations