© 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. 164020
    Prev
    Next
    INDEX
    Explanations

    sinfulness, or place

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

    how things fit

    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
     Gears
    0.47
    砜
    0.47
     কার
    0.46
    labs
    0.45
    ப்படுகிறது
    0.45
     институт
    0.45
    ләү
    0.45
     গিরিশ
    0.45
     понимать
    0.44
     tokamaks
    0.44
    POSITIVE LOGITS
     도착
    0.51
     approu
    0.50
     ich
    0.50
    추
    0.49
     quand
    0.48
     trampled
    0.47
    ৩
    0.46
     hrane
    0.46
     fijo
    0.46
     alimentation
    0.45
    Activations Density 0.000%

    No Known Activations