© 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. 124755
    Prev
    Next
    INDEX
    Explanations

    Eliza, Colleg, Ecole

    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
    ’
    -3.23
     is
    -2.83
     were
    -2.42
    ならず
    -2.38
    you
    -2.34
    蹰
    -2.33
    e
    -2.16
    ).
    -2.16
    complexContent
    -2.13
     lepší
    -2.11
    POSITIVE LOGITS
    0
    3.19
    genodigd
    2.61
    乆
    2.42
    </td>
    2.31
    時的
    2.23
    猻
    2.16
     rajut
    2.16
    5
    2.11
    鉀
    2.09
     oleh
    2.06
    Activations Density 0.001%

    No Known Activations