© 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. 14455
    Prev
    Next
    INDEX
    Explanations

    lorries and possibility

    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
    an
    -2.48
     have
    -2.45
    を含む
    -2.28
     describe
    -2.27
     enjoy
    -2.22
    これらの
    -2.20
     “
    -2.20
     was
    -2.17
     decipher
    -2.17
     define
    -2.16
    POSITIVE LOGITS
    谂
    3.31
    s
    3.31
    很棒
    2.95
    ,"
    2.81
    </h3>
    2.66
    猡
    2.66
    嚒
    2.66
     dekoratif
    2.58
    ↵↵
    2.58
     ministère
    2.48
    Activations Density 0.004%

    No Known Activations