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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60515
    Prev
    Next
    INDEX
    Explanations

    distance and extent

    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
     more
    -1.09
     yerde
    -0.94
    蟠
    -0.90
    ́t
    -0.90
     habitación
    -0.85
     bolj
    -0.84
     farther
    -0.83
    más
    -0.82
     slightly
    -0.81
     hastily
    -0.80
    POSITIVE LOGITS
     into
    1.73
     afield
    1.27
     away
    1.16
    fetched
    1.15
     in
    1.11
     down
    1.03
     towards
    1.02
     back
    1.01
     toward
    0.98
     along
    0.92
    Activations Density 0.016%

    No Known Activations