© 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. 73670
    Prev
    Next
    INDEX
    Explanations

    Easter related terms

    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
    \
    -2.59
    .’
    -2.59
     alrededores
    -2.33
    降临
    -2.23
     szükséges
    -2.20
     גם
    -2.17
    も行
    -2.17
     modalidades
    -2.16
    随后
    -2.13
    鎗
    -2.13
    POSITIVE LOGITS
    磲
    2.98
    鏨
    2.97
    The
    2.67
    𓋼
    2.47
    your
    2.42
    摃
    2.41
    阄
    2.33
    They
    2.31
    these
    2.28
     був
    2.28
    Activations Density 0.004%

    No Known Activations