© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 134050
    Prev
    Next
    INDEX
    Explanations

    specific phrases

    np_acts-logits-general · gemini-2.5-flash-lite

    neurological condition disorders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pronged
    0.44
    ing
    0.44
    वैसे
    0.42
    続いて
    0.40
     रहे
    0.40
    ✶
    0.40
     ਹ
    0.39
     ಅದು
    0.39
    过度
    0.39
     ક્ષ
    0.39
    POSITIVE LOGITS
     oy
    0.49
    ın
    0.46
    报名
    0.45
    Biografia
    0.44
    }</
    0.43
    queira
    0.43
     aşağıdaki
    0.43
    报考
    0.43
    warna
    0.43
    titleTextStyle
    0.42
    Activations Density 0.000%

    No Known Activations