© 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. 70537
    Prev
    Next
    INDEX
    Explanations

    header guards

    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
     their
    -2.17
     using
    -2.05
    </h2>
    -1.88
     the
    -1.84
     any
    -1.84
    </b>
    -1.83
     like
    -1.82
     all
    -1.68
     from
    -1.67
     your
    -1.67
    POSITIVE LOGITS
    着一个
    1.92
     tambien
    1.88
     delegación
    1.88
    がとても
    1.84
     също
    1.80
    なども
    1.77
     
    1.77
     I
    1.76
    形の
    1.76
     cargador
    1.73
    Activations Density 0.047%

    No Known Activations