© 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. 221183
    Prev
    Next
    INDEX
    Explanations

    cat poop

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

    future actions or questions

    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
    qk
    0.46
     acto
    0.46
    σσ
    0.46
     Acts
    0.44
    zący
    0.44
    𝘻
    0.44
    ﺝ
    0.44
     enquire
    0.43
    ς
    0.43
    ພວກເຮ
    0.43
    POSITIVE LOGITS
    りを
    0.50
    died
    0.47
     dáng
    0.46
     어머니
    0.44
     مليون
    0.43
    isselle
    0.43
     स्वभाव
    0.43
    aphyl
    0.42
     சுற்றுச்சூழ
    0.42
    ాన్ని
    0.42
    Activations Density 0.000%

    No Known Activations