© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99586
    Prev
    Next
    INDEX
    Explanations

    private : keyword

    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
     famously
    -1.49
     of
    -1.45
     …
    -1.41
     notoriously
    -1.38
     are
    -1.34
     K
    -1.34
     Закон
    -1.31
     Another
    -1.30
    нення
    -1.30
     We
    -1.30
    POSITIVE LOGITS
    they
    1.77
    also
    1.61
    )
    1.59
    ჻
    1.58
     sendiri
    1.57
    ”,
    1.55
     ersetzt
    1.55
     твои
    1.53
    那些
    1.52
    THEY
    1.52
    Activations Density 0.017%

    No Known Activations