© 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. 87149
    Prev
    Next
    INDEX
    Explanations

    system, design, warranty, hotel

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

    word or concept following

    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
     sacchar
    0.43
    urts
    0.43
     scratching
    0.43
     为了
    0.43
     شاعر
    0.42
     urząd
    0.42
    ="(
    0.41
     সৈনিক
    0.41
     பால்
    0.41
    LIE
    0.41
    POSITIVE LOGITS
    gambar
    0.52
     expliquer
    0.45
     anderer
    0.44
     നില
    0.44
     डीपी
    0.43
    ıyorum
    0.43
     andere
    0.42
     Alternate
    0.42
     ();
    0.42
     entsprechende
    0.42
    Activations Density 0.001%

    No Known Activations