© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98025
    Prev
    Next
    INDEX
    Explanations

    then, need, allowing, owner

    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
    frist
    -0.91
     rése
    -0.86
    idać
    -0.83
     konstant
    -0.83
    gibt
    -0.82
    sistence
    -0.81
     pertama
    -0.81
     contamos
    -0.79
     élevées
    -0.79
     vissza
    -0.78
    POSITIVE LOGITS
     move
    3.77
     moved
    3.08
     proceed
    3.02
     moves
    2.80
    move
    2.78
     moving
    2.73
    Move
    2.50
     Move
    2.47
    Moving
    2.42
     proceeded
    2.41
    Activations Density 0.070%

    No Known Activations