© 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. 98792
    Prev
    Next
    INDEX
    Explanations

    sports categories (points, assists, rebounds)

    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
    ncy
    -0.82
     памя
    -0.81
    appellant
    -0.77
     lietu
    -0.76
    ार्थ
    -0.71
    三十
    -0.70
    вление
    -0.69
    texttt
    -0.69
    もしくは
    -0.68
    offerta
    -0.68
    POSITIVE LOGITS
     steals
    1.70
     steal
    1.46
     Steal
    1.24
     blocks
    1.23
    steal
    1.13
     block
    1.10
    Blocks
    1.08
     thieves
    1.03
     blocked
    1.02
     STE
    1.02
    Activations Density 0.006%

    No Known Activations