© 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. 31258
    Prev
    Next
    INDEX
    Explanations

    explanation or justification

    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
     tahmin
    0.48
     ghat
    0.46
     ఊ
    0.46
     Kalyan
    0.46
    <unused57>
    0.45
     breat
    0.44
     నే
    0.44
     Sudah
    0.43
    犾
    0.42
     നടപ
    0.41
    POSITIVE LOGITS
    ä
    0.50
    ics
    0.46
    andt
    0.46
    and
    0.45
    4
    0.44
    ::~
    0.44
    از
    0.44
    ก
    0.43
    從
    0.43
    ინ
    0.43
    Activations Density 0.005%

    No Known Activations