© 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. 155086
    Prev
    Next
    INDEX
    Explanations

    technical features and craft

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

    where or not

    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
    uu
    0.45
     accue
    0.45
     aren
    0.43
    h
    0.43
     unveiled
    0.43
     accueill
    0.43
     jornada
    0.42
     nouvelle
    0.42
     unveils
    0.42
     academia
    0.41
    POSITIVE LOGITS
    血压
    0.46
    łego
    0.46
    燥
    0.46
     வெப்ப
    0.44
     वही
    0.43
    товой
    0.42
     elution
    0.42
    脨
    0.42
    خدام
    0.42
     Nutr
    0.42
    Activations Density 0.001%

    No Known Activations