© 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. 175968
    Prev
    Next
    INDEX
    Explanations

    Antichrist, beast, buy or sell

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

    666 and Antichrist themes

    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
     വിവിധ
    0.46
    垒
    0.43
    ಿತ
    0.43
     계획
    0.43
    Forum
    0.42
     PLANNING
    0.41
    गराज
    0.41
    计划
    0.41
    䛺
    0.41
     ವಿವಿಧ
    0.41
    POSITIVE LOGITS
     fondness
    0.45
     efficacious
    0.40
     biotechn
    0.40
    endrá
    0.39
     bakter
    0.39
     epitopes
    0.39
    idega
    0.39
    conver
    0.38
    utal
    0.38
    bla
    0.38
    Activations Density 0.007%

    No Known Activations