© 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. 101747
    Prev
    Next
    INDEX
    Explanations

    abbreviations starting with NM

    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
    }
    -3.08
    ーズン
    -2.91
    s
    -2.73
    🙀
    -2.67
     入り口
    -2.67
    😸
    -2.63
    ープン
    -2.61
     カップル
    -2.56
    $*$
    -2.55
    裒
    -2.55
    POSITIVE LOGITS
     the
    3.83
     We
    2.84
    が好き
    2.59
     [(
    2.50
     และ
    2.50
    我也不
    2.48
    とは言
    2.45
    就不是
    2.44
    ка
    2.36
    </b>
    2.31
    Activations Density 0.002%

    No Known Activations