© 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. 111945
    Prev
    Next
    INDEX
    Explanations

    operations in various languages

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

    General settings, specific numbers, or qualitative descriptions

    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
     математи
    0.51
    회
    0.48
     mathematically
    0.47
     mathematical
    0.46
     mathematician
    0.46
    数学
    0.45
     స్
    0.44
    밥
    0.44
     수학
    0.43
    cend
    0.43
    POSITIVE LOGITS
     stallions
    0.48
     alterations
    0.47
     conciertos
    0.47
     vaik
    0.47
    वर्षी
    0.45
    ضب
    0.45
     Supervision
    0.44
     एकज
    0.44
    規劃
    0.44
     opérations
    0.43
    Activations Density 0.001%

    No Known Activations