© 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. 34-GEMMASCOPE-RES-131K
    7. 106196
    Prev
    Next
    INDEX
    Explanations

    the specific part or location

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    などを
    -1.11
     or
    -1.11
    などの
    -0.99
    それでは
    -0.93
    が
    -0.90
    子は
    -0.87
    falgar
    -0.86
    があり
    -0.86
     sneaky
    -0.86
     encontraban
    -0.85
    POSITIVE LOGITS
     both
    1.45
    ditionally
    1.01
     каждой
    0.95
    both
    0.95
    
    0.94
     each
    0.91
    Extremely
    0.90
    oversized
    0.90
    Both
    0.90
    bluza
    0.89
    Activations Density 0.070%

    No Known Activations