© 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. 42548
    Prev
    Next
    INDEX
    Explanations

    led followed by noun

    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
     dalam
    -1.75
    5
    -1.67
     we
    -1.64
     two
    -1.64
    2
    -1.63
    ８
    -1.62
    </i>
    -1.61
    It
    -1.59
    When
    -1.59
    ３
    -1.53
    POSITIVE LOGITS
     nových
    2.17
    沨
    1.92
     We
    1.86
    ଃ
    1.84
    髎
    1.84
    夘
    1.81
    沇
    1.76
    liegenden
    1.75
    
    1.74
     เรา
    1.71
    Activations Density 0.006%

    No Known Activations