© 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. 112043
    Prev
    Next
    INDEX
    Explanations

    names and beginnings of words

    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
     Then
    -3.13
    ).”
    -2.75
     scrutin
    -2.73
     allgemeinen
    -2.50
     berühmten
    -2.48
    好感
    -2.48
    縠
    -2.48
    
    -2.44
    ு
    -2.44
     It
    -2.42
    POSITIVE LOGITS
    s
    3.81
    1
    3.36
    c
    3.30
    *
    3.25
    8
    3.23
    3
    2.95
    5
    2.91
    4
    2.88
    2
    2.84
    ay
    2.72
    Activations Density 0.018%

    No Known Activations