© 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. 67122
    Prev
    Next
    INDEX
    Explanations

    action in progress

    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
     you
    -1.43
     två
    -1.33
    ף
    -1.23
    dA
    -1.23
     dA
    -1.18
     "-",
    -1.12
    財布
    -1.11
    窜
    -1.10
    ziali
    -1.09
     comprender
    -1.08
    POSITIVE LOGITS
     their
    1.58
     any
    1.46
     higher
    1.44
     at
    1.39
     personaggio
    1.30
     famiglia
    1.29
     Handeln
    1.28
     another
    1.27
     nemico
    1.25
     more
    1.24
    Activations Density 0.082%

    No Known Activations