© 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. 119258
    Prev
    Next
    INDEX
    Explanations

    would otherwise be

    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
    Paradox
    -0.81
    TOKYO
    -0.72
     oignon
    -0.70
    liano
    -0.70
    cido
    -0.70
    Transkrypt
    -0.69
     malang
    -0.69
     حوزه
    -0.68
    lementation
    -0.68
     Snell
    -0.67
    POSITIVE LOGITS
     dismiss
    4.50
     dismissed
    4.38
     dismissing
    3.95
     dismissal
    3.73
    dismiss
    3.56
     Dismiss
    3.53
    Dismiss
    3.45
     brushed
    2.92
     brush
    2.86
     shrugged
    2.55
    Activations Density 0.069%

    No Known Activations