© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73573
    Prev
    Next
    INDEX
    Explanations

    types of locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beaches
    -1.14
     dams
    -1.04
     coasts
    -0.96
     shores
    -0.94
    Fallback
    -0.93
     везде
    -0.93
    aimana
    -0.90
     to
    -0.89
     coastal
    -0.89
     verhaal
    -0.88
    POSITIVE LOGITS
     directly
    1.03
    retten
    0.91
    記入
    0.84
     tages
    0.84
     adj
    0.84
     ejes
    0.81
     adjacency
    0.81
     bagay
    0.81
    mô
    0.81
    NoteOnEvent
    0.81
    Activations Density 0.043%

    No Known Activations