© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 3679
    Prev
    Next
    INDEX
    Explanations

    refusal or conditional acceptance

    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_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    䏍
    0.67
     assemblages
    0.66
    บัติ
    0.63
     정확
    0.63
    w
    0.62
    k
    0.62
    n
    0.61
    lasse
    0.61
     دنیا
    0.60
    hv
    0.60
    POSITIVE LOGITS
     reluctance
    0.81
     reluctantly
    0.78
     unwillingness
    0.73
     reluctant
    0.71
     unwilling
    0.69
     refusing
    0.67
    ید
    0.64
    am
    0.63
     on
    0.63
    <0xA4>
    0.61
    Activations Density 0.459%

    No Known Activations