© 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. 22-GEMMASCOPE-RES-131K
    7. 34107
    Prev
    Next
    INDEX
    Explanations

    want something more

    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_22/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
     may
    -1.09
    neurs
    -0.88
     Technically
    -0.86
    ADH
    -0.85
     might
    -0.85
    Geograf
    -0.85
     سعی
    -0.85
     anyone
    -0.84
    There
    -0.81
     Depending
    -0.80
    POSITIVE LOGITS
     σελ
    1.02
    mored
    1.02
     they
    1.01
     davantage
    0.95
     access
    0.95
     Parece
    0.94
     περισσότε
    0.94
    mbal
    0.92
     claridad
    0.91
     more
    0.90
    Activations Density 0.066%

    No Known Activations