© 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. 40-GEMMASCOPE-2-RES-262K
    7. 120145
    Prev
    Next
    INDEX
    Explanations

    communication networks

    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_40_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
     thickly
    0.46
     અથ
    0.40
    ڱ
    0.40
     thick
    0.38
     Psalms
    0.38
    সজ্জিত
    0.38
     épaisse
    0.38
    頻道
    0.38
    瑤
    0.38
    ندی
    0.36
    POSITIVE LOGITS
    Comp
    0.42
     ком
    0.42
    Want
    0.39
    Comm
    0.38
    kom
    0.38
    breed
    0.38
    Kom
    0.38
    Graph
    0.37
    erst
    0.37
    KOM
    0.37
    Activations Density 0.000%

    No Known Activations