© 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. 191760
    Prev
    Next
    INDEX
    Explanations

    transgression, vestiges, RIGHTS

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

    inclusive or changes

    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
    t
    0.56
     do
    0.54
     công
    0.54
     Công
    0.54
     bộ
    0.51
    自己
    0.50
     യൂ
    0.49
    需要
    0.49
     forne
    0.48
     tubes
    0.47
    POSITIVE LOGITS
    ीजन
    0.50
     ਨ
    0.45
     思っ
    0.44
    지에
    0.43
     режими
    0.42
     vestiges
    0.41
    ії
    0.41
     transgression
    0.41
    羢
    0.41
     queryObject
    0.41
    Activations Density 0.001%

    No Known Activations