© 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. 71786
    Prev
    Next
    INDEX
    Explanations

    tends to

    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
    ностях
    -2.08
    锒
    -1.70
    恽
    -1.70
    ၟ
    -1.69
     '')
    -1.66
    ဴ
    -1.66
    ?”
    -1.62
    čku
    -1.58
    ⽩
    -1.57
    茘
    -1.56
    POSITIVE LOGITS
     he
    1.63
     sempre
    1.60
    </sup>
    1.40
     durchaus
    1.37
     wirklich
    1.36
    ↵↵
    1.35
    an
    1.34
    懊
    1.34
    </h4>
    1.33
    oreille
    1.33
    Activations Density 0.021%

    No Known Activations