© 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. 75359
    Prev
    Next
    INDEX
    Explanations

    programmed 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
     yada
    0.50
    现在
    0.48
    ობა
    0.45
    胭
    0.45
     undermines
    0.44
     ausgewählt
    0.44
    шками
    0.43
     playfully
    0.43
     knotted
    0.42
     overcame
    0.42
    POSITIVE LOGITS
    ton
    0.45
    tive
    0.43
    stopwords
    0.42
    AfterTax
    0.42
     L
    0.41
    space
    0.41
    ture
    0.41
    hang
    0.41
    achter
    0.41
    trending
    0.41
    Activations Density 0.032%

    No Known Activations