© 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. 58028
    Prev
    Next
    INDEX
    Explanations

    game board tiles

    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
    Juegos
    -1.02
     retten
    -0.93
     Konkur
    -0.91
    Buckets
    -0.90
    contoh
    -0.90
    teknik
    -0.89
     klasse
    -0.88
    ඥ
    -0.88
    setAll
    -0.88
    Largura
    -0.88
    POSITIVE LOGITS
     cards
    2.02
     card
    1.88
     pieces
    1.70
     tiles
    1.41
     cars
    1.37
     piece
    1.36
     board
    1.33
     player
    1.30
     tile
    1.27
     letter
    1.26
    Activations Density 0.056%

    No Known Activations