© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8523
    Prev
    Next
    INDEX
    Explanations

    para followed by verbs

    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
    潆
    -2.67
    宬
    -2.61
    ꜄
    -2.59
    <bos>
    -2.58
    ?"
    -2.53
    鲧
    -2.50
    '
    -2.48
     of
    -2.48
    眥
    -2.44
     แต่
    -2.42
    POSITIVE LOGITS
    逦
    2.81
    เกง
    2.64
    珦
    2.56
    狃
    2.53
     撮っ
    2.22
     sœur
    2.22
     scattata
    2.20
    鶲
    2.19
    氤
    2.17
    阗
    2.17
    Activations Density 0.004%

    No Known Activations