© 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. 75009
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by titles

    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
     będziesz
    -1.59
    地看着
    -1.49
    It
    -1.48
     universitario
    -1.44
    どうやら
    -1.41
     also
    -1.40
     também
    -1.38
     who
    -1.37
     hiasan
    -1.37
    Nuevas
    -1.35
    POSITIVE LOGITS
     to
    2.05
     their
    1.45
    </h2>
    1.42
     '
    1.37
    ólogo
    1.27
    lagi
    1.27
     each
    1.22
    gem
    1.20
                   
    1.17
    vede
    1.15
    Activations Density 0.033%

    No Known Activations