© 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. 10091
    Prev
    Next
    INDEX
    Explanations

    brand awareness, name, identity, loyalty

    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
    ご予約
    -1.55
     eight
    -1.52
     so
    -1.52
     but
    -1.49
    }
    -1.48
    <bos>
    -1.48
     grünen
    -1.46
    Ƣ
    -1.45
     hauptsächlich
    -1.45
    </h3>
    -1.45
    POSITIVE LOGITS
    щита
    1.95
     deres
    1.87
    Their
    1.77
    訢
    1.69
     exper
    1.61
    !=
    1.61
    力が
    1.60
    </b>
    1.60
     leurs
    1.59
     reaſon
    1.58
    Activations Density 0.014%

    No Known Activations