© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59646
    Prev
    Next
    INDEX
    Explanations

    Maur name variants

    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
    Difference
    -0.73
    ቁ
    -0.71
    Mortal
    -0.71
    甑
    -0.68
    asional
    -0.68
    tellungs
    -0.68
     Forecasts
    -0.68
    台北
    -0.68
    小説
    -0.67
     góc
    -0.67
    POSITIVE LOGITS
     Mau
    0.91
    ricio
    0.86
    mau
    0.75
    स्या
    0.73
     thus
    0.72
    超出
    0.71
     EEG
    0.71
    估
    0.71
     SAS
    0.68
     mau
    0.68
    Activations Density 0.021%

    No Known Activations