© 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. 167913
    Prev
    Next
    INDEX
    Explanations

    Manhattan area, total drop length, Walla County

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

    swallowed whole

    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
     /
    0.57
    im
    0.54
    ay
    0.54
    ue
    0.54
    ig
    0.53
    ze
    0.53
    ine
    0.52
    ie
    0.52
    ell
    0.52
    0.52
    POSITIVE LOGITS
     vedit
    0.59
     místě
    0.58
     odkazy
    0.56
    逺
    0.55
     detalhes
    0.55
     అన్ని
    0.55
     errado
    0.55
     mük
    0.54
     ascendent
    0.54
     ભાગ
    0.53
    Activations Density 0.001%

    No Known Activations