© 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. 229604
    Prev
    Next
    INDEX
    Explanations

    Spirit Nights

    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
     Transporte
    0.51
     Landkreis
    0.49
    "
    0.49
     அவற்றில்
    0.47
     Acerca
    0.46
     Blessed
    0.45
     Bereich
    0.45
     Area
    0.45
     Playlist
    0.45
    Ꮲ
    0.45
    POSITIVE LOGITS
     hadrons
    0.45
    เซล
    0.44
    itarian
    0.44
     dehydrogenase
    0.42
     پاسخ
    0.42
     wavefront
    0.42
     бар
    0.42
     aspirin
    0.42
     phenyl
    0.42
    वाणी
    0.42
    Activations Density 0.001%

    No Known Activations