© 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. 26697
    Prev
    Next
    INDEX
    Explanations

    moving silently, sneaking

    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
    出力
    0.44
    HEMAT
    0.44
     prosa
    0.43
    빻
    0.42
     utopian
    0.41
     recal
    0.41
    励
    0.41
     refractory
    0.40
    鵡
    0.40
     resonated
    0.39
    POSITIVE LOGITS
     stealth
    1.94
     Stealth
    1.60
     sneak
    1.41
     sneaking
    1.32
     sneaky
    1.23
     Sne
    1.14
    sneak
    1.14
    蹑
    1.12
     silently
    1.11
    Sne
    1.09
    Activations Density 0.023%

    No Known Activations