© 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. 40162
    Prev
    Next
    INDEX
    Explanations

    technical noun phrases

    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
    ︲
    -1.48
    newblock
    -1.46
    找个
    -1.45
    ⬈
    -1.45
     nieuwe
    -1.44
     ſel
    -1.38
     kinda
    -1.38
    问问
    -1.38
     eſt
    -1.37
     budete
    -1.37
    POSITIVE LOGITS
     by
    1.92
     both
    1.83
     TWO
    1.59
    Both
    1.47
     our
    1.45
     BOTH
    1.42
     this
    1.37
     EVERY
    1.37
     unequivocally
    1.36
    Ironically
    1.34
    Activations Density 0.190%

    No Known Activations