© 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. 67004
    Prev
    Next
    INDEX
    Explanations

    ego identity or ego trips

    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
    訁
    -2.72
     were
    -2.67
    抔
    -2.64
     purpoſe
    -2.53
     he
    -2.44
    哢
    -2.44
    祤
    -2.41
     sce
    -2.38
     劇場
    -2.36
    </b>
    -2.34
    POSITIVE LOGITS
     berdua
    2.44
    ۠
    2.41
    😇
    2.33
    𓍊
    2.22
    ﹍﹍
    2.19
     bénévol
    2.17
    ⦊
    2.17
     sucedió
    2.14
    ႐
    2.13
    栊
    1.98
    Activations Density 0.001%

    No Known Activations