© 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-TRANSCODER-262K
    7. 221009
    Prev
    Next
    INDEX
    Explanations

    refusal or rejection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    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
    )\|
    0.42
    ซิตี
    0.38
    izquierda
    0.35
     hablaremos
    0.35
     ciudades
    0.34
    Selecion
    0.34
     Chọn
    0.34
    を下
    0.34
     cidade
    0.34
     beforeEach
    0.33
    POSITIVE LOGITS
     refusal
    0.62
     refus
    0.59
     rejection
    0.56
     denials
    0.48
     denial
    0.46
    拒
    0.44
     resistance
    0.43
     reluctance
    0.43
     réponse
    0.43
     negatives
    0.42
    Activations Density 0.037%

    No Known Activations