© 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. 86550
    Prev
    Next
    INDEX
    Explanations

    of a

    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
     CuO
    0.54
    ᄈ
    0.53
     mortars
    0.53
     muffins
    0.49
    FlowNode
    0.47
    notepad
    0.47
     contaminant
    0.47
    Bol
    0.47
    Iteration
    0.47
     ricotta
    0.47
    POSITIVE LOGITS
    ara
    0.64
     \
    0.62
     п
    0.60
     в
    0.58
    yı
    0.57
    ૨
    0.57
     पर
    0.56
    నున్న
    0.56
    amaya
    0.56
     ല
    0.55
    Activations Density 0.000%

    No Known Activations