© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86058
    Prev
    Next
    INDEX
    Explanations

    prince, princess, or highness

    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
    </strong>
    -1.49
    res
    -1.48
     admires
    -1.39
    余談
    -1.38
     itself
    -1.35
     introduces
    -1.31
    也會
    -1.28
    いけない
    -1.25
    他知道
    -1.25
    鶿
    -1.24
    POSITIVE LOGITS
     who
    1.38
    殇
    1.38
     शुर
    1.35
     február
    1.34
     instead
    1.34
    )}$.
    1.31
    entri
    1.26
    妹
    1.26
     without
    1.24
     rather
    1.24
    Activations Density 0.028%

    No Known Activations