© 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. 31-GEMMASCOPE-2-RES-65K
    7. 30718
    Prev
    Next
    INDEX
    Explanations

    describing negative events or states

    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_65k_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
     harnesses
    0.50
     Tomcat
    0.48
     a
    0.47
     mayores
    0.47
     by
    0.46
     Blazers
    0.45
     Gates
    0.45
     to
    0.44
     struck
    0.44
     `<`,
    0.44
    POSITIVE LOGITS
    จะไม่
    0.52
    rime
    0.49
    Reconnect
    0.48
    </h4>
    0.47
    сит
    0.45
    </th>
    0.44
     गं
    0.44
    Injection
    0.44
    🌏
    0.44
     ممکن
    0.43
    Activations Density 0.015%

    No Known Activations