© 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. 52241
    Prev
    Next
    INDEX
    Explanations

    wrongdoing, distrust, expanding, metal, allows

    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
     assemblages
    0.42
     climate
    0.42
     when
    0.41
     bi
    0.40
    climate
    0.40
    計劃
    0.40
    疊
    0.39
    轉
    0.39
    對
    0.39
     dialect
    0.38
    POSITIVE LOGITS
     characterised
    0.41
     estándar
    0.38
     সাজ
    0.38
    ähän
    0.37
     Boynton
    0.36
     അല്ലെങ്കിൽ
    0.36
    ㄚ
    0.36
     advisable
    0.35
    amız
    0.35
     Enumer
    0.35
    Activations Density 0.009%

    No Known Activations