© 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. 8379
    Prev
    Next
    INDEX
    Explanations

    tend to verb

    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
     this
    -1.98
     one
    -1.90
     there
    -1.39
     no
    -1.38
     could
    -1.36
     can
    -1.35
     Perhaps
    -1.31
     Such
    -1.30
    ях
    -1.27
     Probably
    -1.27
    POSITIVE LOGITS
    если
    1.52
    只是
    1.45
     excès
    1.41
    très
    1.41
     abbildung
    1.41
    revealed
    1.38
    depends
    1.37
    ONLY
    1.36
     چیز
    1.34
    couverte
    1.34
    Activations Density 0.031%

    No Known Activations