© 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. 118822
    Prev
    Next
    INDEX
    Explanations

    interface to systems or other interfaces

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "interface" in technical or scientific contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    ’
    -2.97
    ’,
    -2.83
    </i>
    -2.78
    ’;
    -2.67
    鬭
    -2.53
     verkau
    -2.47
    出てくる
    -2.45
    ため
    -2.44
    an
    -2.41
     
    -2.39
    POSITIVE LOGITS
    籐
    2.91
     chileno
    2.91
     peruano
    2.81
     brasileño
    2.81
    猹
    2.67
    镚
    2.66
     colombiano
    2.58
    ')
    2.58
    BITDA
    2.55
    肏
    2.55
    Activations Density 0.016%

    No Known Activations