© 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. 75946
    Prev
    Next
    INDEX
    Explanations

    player or players

    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
    gadier
    -0.86
    ,**
    -0.81
    noticia
    -0.77
    urro
    -0.75
     notables
    -0.75
    RIDE
    -0.75
     staffers
    -0.74
     larynx
    -0.74
     genutzt
    -0.74
     ребята
    -0.73
    POSITIVE LOGITS
     player
    4.25
     players
    3.31
     Player
    3.20
    Player
    3.00
    player
    2.84
     PLAYER
    2.55
    PLAYER
    2.47
     Players
    2.30
     jugador
    2.23
    getPlayer
    2.16
    Activations Density 0.029%

    No Known Activations