© 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. 63072
    Prev
    Next
    INDEX
    Explanations

    proper names and titles

    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
    when
    -1.13
     также
    -0.98
    Ито
    -0.95
    Also
    -0.94
    Интере
    -0.91
    噫
    -0.91
    Примі
    -0.90
     también
    -0.90
    Джерело
    -0.88
     cũng
    -0.88
    POSITIVE LOGITS
    abonnement
    1.05
     majestic
    1.05
    बस
    1.01
     tumultuous
    0.98
     horrible
    0.98
    霸
    0.97
     mediocre
    0.97
     trusty
    0.95
     creators
    0.94
    erent
    0.93
    Activations Density 0.000%

    No Known Activations