© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78888
    Prev
    Next
    INDEX
    Explanations

    0000 codes

    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
    Not in Any Lists

    No Comments

    Negative Logits
     even
    -1.20
     both
    -1.11
     from
    -1.09
     one
    -1.04
     any
    -1.03
     in
    -1.01
    Even
    -1.01
     already
    -0.98
     at
    -0.97
     bereits
    -0.97
    POSITIVE LOGITS
    iedene
    0.96
     verschiedenen
    0.95
     différentes
    0.92
     okazji
    0.90
     luscious
    0.90
     consideración
    0.88
     différents
    0.88
    דות
    0.87
     olika
    0.86
     sitesinde
    0.85
    Activations Density 0.006%

    No Known Activations