© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130144
    Prev
    Next
    INDEX
    Explanations

    Elias, elapsed, Ago

    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
     appeler
    -2.36
     ongeveer
    -2.36
     indiquer
    -2.31
    嶮
    -2.28
     ファイル
    -2.28
     présenter
    -2.28
    </b>
    -2.25
    蟥
    -2.25
     aspek
    -2.17
    晄
    -2.17
    POSITIVE LOGITS
    写真は
    2.75
    ポイントは
    2.58
    鼕
    2.47
    ᯅ
    2.44
     Not
    2.44
    敍
    2.33
    it
    2.30
     emp
    2.11
    $*$
    2.11
    不宜
    2.09
    Activations Density 0.002%

    No Known Activations