© 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
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 32107
    Prev
    Next
    INDEX
    Explanations

    one after another

    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
    은
    0.47
    asset
    0.46
    奠
    0.46
    setRoot
    0.44
    首先
    0.43
    a
    0.43
    ಿದ್ದರೆ
    0.42
    oplast
    0.42
    jord
    0.42
    jPanel
    0.42
    POSITIVE LOGITS
     effectiveness
    0.53
     agg
    0.52
     yang
    0.52
     ory
    0.52
     liters
    0.50
     kal
    0.50
     yin
    0.50
    T
    0.49
     natural
    0.49
     terutama
    0.49
    Activations Density 0.000%

    No Known Activations