© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 220933
    Prev
    Next
    INDEX
    Explanations

    surveillance detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     пона
    0.47
     мони
    0.45
    亅
    0.43
    லோச
    0.43
     күзгү
    0.43
    monitor
    0.42
    IAB
    0.41
    monitoring
    0.40
    āb
    0.40
    稽
    0.39
    POSITIVE LOGITS
    ille
    0.46
    U
    0.43
     tech
    0.42
     Auflage
    0.42
    ich
    0.42
     equipment
    0.41
     tout
    0.41
    '
    0.41
     Relaxation
    0.40
     Jillian
    0.40
    Activations Density 0.003%

    No Known Activations