© 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. 229682
    Prev
    Next
    INDEX
    Explanations

    needed locksmith or replacement

    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
    chest
    0.43
     CHEMICAL
    0.42
     CERT
    0.42
    wealth
    0.41
     COLOR
    0.41
    0.41
    tif
    0.41
     Fem
    0.40
     Chemical
    0.40
     richesse
    0.40
    POSITIVE LOGITS
    л
    0.49
     stades
    0.48
     incub
    0.48
    μι
    0.47
     congen
    0.47
    ιλ
    0.45
     subjet
    0.45
     approxim
    0.45
    asyarakat
    0.44
    ਾਕ
    0.44
    Activations Density 0.002%

    No Known Activations