© 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-262K
    7. 4447
    Prev
    Next
    INDEX
    Explanations

    deliberate disruption or refusal

    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
    %
    0.40
    ول
    0.37
    奋
    0.37
    சன்
    0.35
    阐
    0.34
     특징
    0.34
     isom
    0.34
    }
    0.33
    玄
    0.32
    深刻
    0.32
    POSITIVE LOGITS
     refused
    0.64
     refuses
    0.62
     disrespect
    0.61
     refuse
    0.61
     maliciously
    0.60
     disrespectful
    0.58
     sabotage
    0.57
     disregard
    0.57
     purposely
    0.56
     deliberately
    0.56
    Activations Density 0.110%

    No Known Activations