© 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. 10-GEMMASCOPE-RES-131K
    4. 90880
    Prev
    Next
    INDEX
    Explanations

    how or what followed by a noun phrase

    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
    ']
    -1.71
    }$
    -1.62
     a
    -1.61
     aficionados
    -1.53
    );
    -1.48
    </td>
    -1.46
    }
    -1.45
    man
    -1.44
     Austr
    -1.44
    us
    -1.42
    POSITIVE LOGITS
     other
    2.03
     there
    1.67
    Other
    1.66
     newest
    1.57
     examples
    1.48
     images
    1.46
     fashionable
    1.44
    古风
    1.44
     most
    1.43
     creative
    1.41
    Activations Density 0.011%

    No Known Activations