© 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. 117532
    Prev
    Next
    INDEX
    Explanations

    dates and months

    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
     ký
    -0.88
    roba
    -0.80
    missão
    -0.80
     indicadores
    -0.79
    дання
    -0.79
     hochwer
    -0.76
    ByEmail
    -0.75
     diesmal
    -0.75
    vité
    -0.75
    CROSSTALK
    -0.74
    POSITIVE LOGITS
     governmental
    0.96
     lära
    0.94
    presenter
    0.93
    ligheten
    0.92
    Inde
    0.92
    LIP
    0.89
     gover
    0.89
     armon
    0.88
     Rashford
    0.86
     adep
    0.86
    Activations Density 0.001%

    No Known Activations