© 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-65K
    7. 30966
    Prev
    Next
    INDEX
    Explanations

    non-committal phrases and admissions

    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_65k_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
     здравоохра
    0.48
    a
    0.47
    ה
    0.45
    -*/
    0.44
    ꯌ
    0.43
    enan
    0.42
     اجتماعی
    0.42
    enment
    0.41
     Toán
    0.41
    ा
    0.41
    POSITIVE LOGITS
     avocados
    0.45
    ර්ග
    0.42
    ων
    0.41
     controversial
    0.39
     космо
    0.39
     edgy
    0.39
     mass
    0.38
     vape
    0.38
     ingredients
    0.38
    屏幕
    0.38
    Activations Density 0.001%

    No Known Activations