© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19250
    Prev
    Next
    INDEX
    Explanations

    cynicism, skepticism, and distrust

    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_31_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
    馋
    0.46
     QnrB
    0.45
    cznej
    0.44
    ه
    0.43
    凿
    0.42
    実
    0.42
    тные
    0.41
    др
    0.41
    ற
    0.41
    ୍ର
    0.40
    POSITIVE LOGITS
     Wu
    0.47
     ulo
    0.45
     gimana
    0.45
     Fresno
    0.45
     extortion
    0.44
     liste
    0.43
     satirical
    0.43
     Dallas
    0.43
     প্রবন্ধ
    0.42
    r
    0.42
    Activations Density 0.000%

    No Known Activations