© 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. 63499
    Prev
    Next
    INDEX
    Explanations

    counting or included

    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
    OPLE
    -0.73
    mą
    -0.73
     Heidi
    -0.72
    ⊡
    -0.72
     Omn
    -0.69
    Biografie
    -0.69
     Nights
    -0.69
    ដ
    -0.68
     există
    -0.68
    chwyd
    -0.68
    POSITIVE LOGITS
     count
    2.77
    count
    2.45
     Count
    2.13
     rely
    1.97
    Count
    1.95
     counts
    1.91
     compter
    1.85
     counted
    1.83
    COUNT
    1.80
     counting
    1.74
    Activations Density 0.009%

    No Known Activations