© 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. 31-GEMMASCOPE-2-RES-262K
    7. 203090
    Prev
    Next
    INDEX
    Explanations

    code imports and system calls

    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_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
     ఏ
    0.45
     bho
    0.44
     अख
    0.43
    on
    0.42
     如
    0.41
     တ
    0.41
     आरोपित
    0.40
     mắc
    0.40
     美国
    0.40
     بع
    0.39
    POSITIVE LOGITS
    ளிர்
    0.46
    я
    0.44
     linea
    0.43
    leftChild
    0.41
    स्वास्थ्य
    0.40
     offsetY
    0.40
     रुच
    0.39
    σ
    0.39
    ライン
    0.39
    ш
    0.39
    Activations Density 0.001%

    No Known Activations