© 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. 191525
    Prev
    Next
    INDEX
    Explanations

    disruptions move

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

    greed, revenge, liability, age

    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
    assuming
    0.45
    none
    0.44
     охорони
    0.44
    atalog
    0.43
     木
    0.43
    denes
    0.43
    ducation
    0.41
    簾
    0.41
    lectric
    0.40
     얘가
    0.40
    POSITIVE LOGITS
     представля
    0.50
    തി
    0.48
     جہاں
    0.48
    тари
    0.48
    தமிழ
    0.47
     limitado
    0.47
     rappresenta
    0.46
     przet
    0.46
     représentent
    0.46
    ע
    0.46
    Activations Density 0.000%

    No Known Activations