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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 262
    Prev
    Next
    INDEX
    Explanations

    names, places, or concepts

    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
    रेज
    0.26
    zovaniyu
    0.23
     τρόπο
    0.22
    敉
    0.21
     PROBLEMS
    0.21
    Variance
    0.21
    ጋገብ
    0.21
    betriebnahme
    0.21
     गेंदबाजों
    0.21
    合せ
    0.21
    POSITIVE LOGITS
     B
    0.28
     S
    0.28
     K
    0.26
     L
    0.26
     D
    0.25
     St
    0.25
     M
    0.25
     C
    0.25
    ena
    0.25
     V
    0.24
    Activations Density 0.104%

    No Known Activations