© 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. 22-GEMMASCOPE-RES-131K
    4. 11052
    Prev
    Next
    INDEX
    Explanations

    code and markup structures

    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_22/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
     to
    -1.93
    鱈
    -1.70
     for
    -1.64
     one
    -1.63
     two
    -1.57
     by
    -1.55
    _
    -1.53
     There
    -1.52
     several
    -1.51
     all
    -1.48
    POSITIVE LOGITS
    </h3>
    1.84
    ↵
    1.84
    AL
    1.80
    杈
    1.70
     actualizar
    1.55
    ꜆
    1.55
    “…
    1.55
    Etape
    1.53
    genen
    1.52
     desactivar
    1.51
    Activations Density 0.002%

    No Known Activations