© 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. 3351
    Prev
    Next
    INDEX
    Explanations

    email recipients and addresses

    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
    OrUpdate
    -0.69
     keting
    -0.68
    return
    -0.67
     set
    -0.66
     skupiny
    -0.65
    ૬
    -0.65
     return
    -0.64
     гро
    -0.63
    SOFTWARE
    -0.63
     buenas
    -0.62
    POSITIVE LOGITS
    HKEY
    0.76
     離
    0.67
     Edge
    0.66
    <0x83>
    0.66
     centrally
    0.65
    VEC
    0.65
    ValuePair
    0.64
    icioso
    0.64
    cutter
    0.64
    kler
    0.63
    Activations Density 0.058%

    No Known Activations