© 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. 69687
    Prev
    Next
    INDEX
    Explanations

    buy both

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

    humans, guilt, bells, preserving, coins

    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
    0.51
    (
    0.46
     fraud
    0.45
    ศัก
    0.42
    你也
    0.42
     VISA
    0.42
     kinase
    0.41
    我会
    0.41
    ני
    0.41
    ^{(\
    0.40
    POSITIVE LOGITS
     düz
    0.50
     கட்டடக்கலை
    0.49
    bz
    0.49
     વિસ્ત
    0.49
     Seç
    0.48
    iction
    0.48
    suz
    0.46
     tornar
    0.46
    pars
    0.45
     நட்பு
    0.45
    Activations Density 0.001%

    No Known Activations