© 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. 32691
    Prev
    Next
    INDEX
    Explanations

    foreign minister, dehumidifier, already, Kuryakyn

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

    descriptions and informational snippets

    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
    ग
    0.52
    د
    0.46
     came
    0.44
    ставьте
    0.44
    ेलकम
    0.44
     ஆட்சிய
    0.44
     Vanguard
    0.42
    حظ
    0.42
     shade
    0.41
    न्यास
    0.41
    POSITIVE LOGITS
    lished
    0.51
    船舶
    0.47
    <0x1D>
    0.46
    
    0.46
    ourses
    0.44
     পরবর্তী
    0.44
    <0x18>
    0.43
     européenne
    0.43
     여름
    0.43
    
    0.43
    Activations Density 0.000%

    No Known Activations