© 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. 201295
    Prev
    Next
    INDEX
    Explanations

    central authority, hot water, compliance

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

    code definitions and calculations

    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
    ä
    0.45
    imiter
    0.45
     अ
    0.43
     ਲ
    0.42
     रात्रि
    0.42
     а
    0.41
     अंबानी
    0.41
    psi
    0.41
    Fir
    0.40
     장
    0.40
    POSITIVE LOGITS
     entornos
    0.49
     culturas
    0.47
    ্যন্তরীণ
    0.45
    ين
    0.44
     unterschied
    0.44
    الك
    0.44
     schnell
    0.43
     عدد
    0.43
    كيف
    0.43
    وين
    0.43
    Activations Density 0.001%

    No Known Activations