© 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. 10-GEMMASCOPE-RES-131K
    7. 68282
    Prev
    Next
    INDEX
    Explanations

    initial stages

    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
    inning
    -1.50
    たくない
    -1.42
     água
    -1.42
    냑
    -1.37
    during
    -1.36
    viembre
    -1.32
     ACCIDENT
    -1.28
    튿
    -1.28
     esquerdo
    -1.28
    according
    -1.28
    POSITIVE LOGITS
     now
    1.61
     out
    1.46
     as
    1.44
     rough
    1.33
     over
    1.30
    y
    1.28
    '
    1.27
    ers
    1.26
     ideas
    1.26
     while
    1.25
    Activations Density 0.057%

    No Known Activations