© 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. 90814
    Prev
    Next
    INDEX
    Explanations

    Lord, understanding, guys, Martin, which, must

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

    phrases following common words

    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
     overr
    0.53
     độ
    0.49
    یمپ
    0.48
    cą
    0.46
     pozit
    0.45
     avantaj
    0.44
    ^*_{
    0.44
    ন্টে
    0.44
    نع
    0.43
     questões
    0.43
    POSITIVE LOGITS
     लगे
    0.44
     I
    0.43
     blossoming
    0.43
    ത്ത
    0.42
     জারি
    0.41
     ይች
    0.40
     flowering
    0.40
     செய்
    0.40
    arbeitung
    0.40
     giddy
    0.40
    Activations Density 0.000%

    No Known Activations