© 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. 10-GEMMASCOPE-RES-131K
    7. 11021
    Prev
    Next
    INDEX
    Explanations

    dates and ranges

    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_10/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
     \&
    -2.34
    ſſen
    -1.94
    ᮣ
    -1.89
    ⃑
    -1.83
    jeuner
    -1.80
    zembro
    -1.79
     comunica
    -1.79
    ＄
    -1.76
    
    -1.76
    FONTE
    -1.75
    POSITIVE LOGITS
    b
    2.59
    c
    2.06
     These
    2.00
    y
    2.00
    a
    1.99
    d
    1.98
    h
    1.95
     it
    1.86
    on
    1.86
     Several
    1.84
    Activations Density 0.009%

    No Known Activations