© 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. 62690
    Prev
    Next
    INDEX
    Explanations

    indices, sequences, or terms

    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
     how
    -0.91
    WriteTo
    -0.85
     tänker
    -0.83
     pelaksanaan
    -0.82
    ági
    -0.77
     notwithstanding
    -0.77
    .³
    -0.76
     nonetheless
    -0.75
    煮
    -0.74
    lng
    -0.74
    POSITIVE LOGITS
     another
    1.07
    nother
    0.95
    Another
    0.94
    另一个
    0.93
     Übere
    0.91
    another
    0.88
     دیگری
    0.88
     otro
    0.86
     next
    0.83
    jain
    0.82
    Activations Density 0.020%

    No Known Activations