© 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. 10-GEMMASCOPE-RES-131K
    7. 73980
    Prev
    Next
    INDEX
    Explanations

    that followed by a noun

    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
    竺
    -1.40
     woord
    -1.34
     eten
    -1.33
    sometimes
    -1.30
     vaak
    -1.26
     mètres
    -1.25
    ཥ
    -1.25
    ∖
    -1.24
     aussit
    -1.23
    碛
    -1.23
    POSITIVE LOGITS
     there
    1.63
     this
    1.62
     if
    1.47
     any
    1.41
     suitable
    1.37
     because
    1.36
     specific
    1.36
     has
    1.32
     different
    1.27
     designated
    1.27
    Activations Density 0.058%

    No Known Activations