© 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. 41-GEMMASCOPE-2-RES-262K
    7. 22680
    Prev
    Next
    INDEX
    Explanations

    Ret words

    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_all/layer_41_width_262k_l0_big
    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
    㜿
    0.45
     الرجل
    0.41
     उपलब्धि
    0.41
    ід
    0.39
    িষ্ট
    0.39
     renouvel
    0.39
    ubert
    0.38
     técnicos
    0.37
     Державний
    0.37
     rehabilitación
    0.37
    POSITIVE LOGITS
    Ret
    0.86
     Ret
    0.85
     ret
    0.83
     RET
    0.73
    ret
    0.68
    退
    0.61
     퇴
    0.59
     reti
    0.55
    or
    0.51
     retin
    0.50
    Activations Density 0.006%

    No Known Activations