© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 54250
    Prev
    Next
    INDEX
    Explanations

    refuse or refusal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     möge
    -0.88
    ГЛА
    -0.85
    amela
    -0.84
    lıkla
    -0.82
    ombo
    -0.80
    Kako
    -0.79
    ultier
    -0.79
     condamné
    -0.77
     laissé
    -0.76
     akşam
    -0.76
    POSITIVE LOGITS
     refuse
    5.97
     refuses
    5.78
     refused
    5.78
     refusal
    5.66
     refusing
    5.53
     refus
    4.44
     Refuse
    4.41
     unwillingness
    3.64
    拒绝
    3.48
     отказа
    3.41
    Activations Density 0.125%

    No Known Activations