© 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. 146757
    Prev
    Next
    INDEX
    Explanations

    default, generally choose, lunch breaks, lemon peels

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

    shadow detection or employee attempts

    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
    Officials
    0.44
    Edward
    0.44
    Brett
    0.43
     excavator
    0.43
    Were
    0.42
     বাস্তবে
    0.42
    Mens
    0.41
     această
    0.40
    梫
    0.40
    ╬
    0.40
    POSITIVE LOGITS
    idos
    0.51
     उपलब्धता
    0.49
    制品
    0.48
    obal
    0.48
     múltiplos
    0.47
    ajos
    0.47
    ្នក
    0.47
     రెండో
    0.46
    ogr
    0.46
    ár
    0.45
    Activations Density 0.001%

    No Known Activations