© 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. 162952
    Prev
    Next
    INDEX
    Explanations

    dangerous offender

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

    QC followed by postal code

    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
     플
    0.47
    spunkt
    0.47
     먹
    0.46
     Certainly
    0.46
    淄
    0.45
     cauliflower
    0.44
     ተግባ
    0.44
     გას
    0.44
    플
    0.44
     निवेदन
    0.43
    POSITIVE LOGITS
    જ
    0.60
    विज्ञापन
    0.49
     mắt
    0.49
    WEL
    0.49
    REME
    0.47
     anc
    0.46
     outro
    0.46
     tante
    0.46
     extinct
    0.46
     outra
    0.45
    Activations Density 0.000%

    No Known Activations