© 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. 124158
    Prev
    Next
    INDEX
    Explanations

    I want

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

    sloping, running average

    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
     вали
    0.47
     запах
    0.47
    FileURL
    0.46
     ставок
    0.45
     শক্তি
    0.45
    כה
    0.45
    ustainable
    0.44
    㓩
    0.44
     взрос
    0.44
     молока
    0.44
    POSITIVE LOGITS
    at
    0.53
     reports
    0.51
     described
    0.50
     travaux
    0.49
     alguns
    0.48
     bapt
    0.47
     works
    0.46
     sou
    0.46
     yn
    0.45
     termes
    0.45
    Activations Density 0.000%

    No Known Activations