© 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. 58678
    Prev
    Next
    INDEX
    Explanations

    just like analogies

    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
    '],
    -2.52
     This
    -2.09
    </em>
    -2.09
    ↵↵
    -2.00
     mycket
    -1.83
    察觉
    -1.77
    .';
    -1.77
    但这
    -1.76
     sebagainya
    -1.74
    )
    -1.73
    POSITIVE LOGITS
    しました
    2.13
     how
    2.06
     they
    1.90
    俢
    1.80
    位の
    1.79
     that
    1.78
     the
    1.74
    卨
    1.72
     your
    1.68
    u
    1.68
    Activations Density 0.008%

    No Known Activations