© 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. 90208
    Prev
    Next
    INDEX
    Explanations

    skin warts

    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
    ेन्द्र
    0.44
    三個
    0.40
     பல்
    0.40
    様々な
    0.40
     قاعده
    0.39
    íe
    0.39
    érience
    0.38
    ༅
    0.38
     ব্যবসা
    0.38
     Literally
    0.38
    POSITIVE LOGITS
     cortes
    0.54
     requiere
    0.51
     pertanto
    0.50
     necesitan
    0.50
     senator
    0.49
     certificado
    0.48
     convoc
    0.47
     requieren
    0.47
     rotate
    0.46
     necesita
    0.46
    Activations Density 0.009%

    No Known Activations