© 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. 69820
    Prev
    Next
    INDEX
    Explanations

    plug hole location

    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
    CommandHandler
    -1.38
     feminina
    -1.38
     prosjek
    -1.37
     commencé
    -1.36
    ="";
    -1.33
     Romania
    -1.32
     pouvaient
    -1.30
    (__('
    -1.29
    ítja
    -1.27
     sommar
    -1.27
    POSITIVE LOGITS
     for
    2.28
     at
    2.14
     in
    1.87
     each
    1.44
     both
    1.39
     there
    1.30
     miliardi
    1.29
     affari
    1.27
     the
    1.27
     doing
    1.23
    Activations Density 0.036%

    No Known Activations