© 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. 208377
    Prev
    Next
    INDEX
    Explanations

    legal partnership

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

    proposed or hypothetical scenarios

    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
     שלנו
    0.49
     السابع
    0.46
     esenciales
    0.45
    లిన
    0.45
    镗
    0.45
    וני
    0.44
     yếu
    0.44
     שלו
    0.44
    вое
    0.44
    ንዱ
    0.43
    POSITIVE LOGITS
    >,
    0.47
    f
    0.46
    stw
    0.42
    emetery
    0.42
     Bingo
    0.42
    VST
    0.41
     Crawley
    0.41
    heast
    0.41
     वर्ग
    0.41
    してから
    0.41
    Activations Density 0.000%

    No Known Activations