© 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. 22-GEMMASCOPE-RES-131K
    7. 39079
    Prev
    Next
    INDEX
    Explanations

    default, blank, University Professor

    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
     these
    -1.18
     it
    -1.05
    果汁
    -0.98
    知道
    -0.98
     in
    -0.95
     about
    -0.95
    它的
    -0.95
     since
    -0.94
     up
    -0.91
    חן
    -0.90
    POSITIVE LOGITS
     сейчас
    1.06
    »).
    0.98
     Ucraina
    0.96
    看着他
    0.96
     ราคา
    0.95
    iction
    0.93
     Geografia
    0.93
     agir
    0.92
    Nazionale
    0.92
    場所に
    0.91
    Activations Density 0.000%

    No Known Activations