© 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. 249747
    Prev
    Next
    INDEX
    Explanations

    specific word followed by comma or related word

    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
     көп
    0.54
     রোজ
    0.53
     SIINFEKL
    0.50
     ሽፋን
    0.50
    Deborah
    0.49
    ডো
    0.48
    किसान
    0.48
     કો
    0.48
     채
    0.48
    SignedIn
    0.48
    POSITIVE LOGITS
    acity
    0.48
    cas
    0.48
    น้อง
    0.45
     Zo
    0.43
     horizont
    0.42
    ier
    0.42
    ogenes
    0.41
    kar
    0.41
    gers
    0.40
    beds
    0.40
    Activations Density 0.001%

    No Known Activations