© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 183064
    Prev
    Next
    INDEX
    Explanations

    street tango dancers

    np_acts-logits-general · gemini-2.5-flash-lite

    PCI DSS compliant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     assunto
    0.52
     alright
    0.49
     afficher
    0.48
     iteratively
    0.48
     Dalib
    0.47
    geving
    0.47
     effektiv
    0.47
     chival
    0.46
     unattainable
    0.46
    襬
    0.45
    POSITIVE LOGITS
     دونك
    0.46
     теннис
    0.46
    ructive
    0.44
    يب
    0.43
     уве
    0.43
     பெ
    0.43
     स्पोर्ट्स
    0.43
    ።
    0.43
    পাতের
    0.42
     জানে
    0.42
    Activations Density 0.000%

    No Known Activations