© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75612
    Prev
    Next
    INDEX
    Explanations

    program execution

    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
     for
    -2.50
     because
    -2.47
     and
    -2.27
     after
    -2.05
     When
    -1.98
     from
    -1.96
     get
    -1.92
     has
    -1.91
     makes
    -1.88
     
    -1.84
    POSITIVE LOGITS
     requerimientos
    2.34
     "}";
    1.91
     our
    1.91
     arrêter
    1.89
    えっ
    1.88
    kinda
    1.85
     estándares
    1.84
     apprécier
    1.83
     cieka
    1.81
     puertos
    1.81
    Activations Density 0.064%

    No Known Activations