© 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. 68083
    Prev
    Next
    INDEX
    Explanations

    orientation corresponds

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

    improvement and enhancement

    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
     Homeland
    0.47
    联合国
    0.46
    genesis
    0.46
    bala
    0.45
    Genesis
    0.45
    zeit
    0.43
    termin
    0.43
    ());
    0.42
    ാരം
    0.42
     состоялась
    0.42
    POSITIVE LOGITS
     raspberry
    0.52
    ैम
    0.51
     quinquina
    0.51
     lymphocyte
    0.50
     bebas
    0.50
     panther
    0.50
     phenytoin
    0.49
     you
    0.49
     unequivocally
    0.49
     unequiv
    0.49
    Activations Density 0.001%

    No Known Activations