© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74736
    Prev
    Next
    INDEX
    Explanations

    compiled record averaged

    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
    殽
    -1.72
    ),"
    -1.65
    Ꮄ
    -1.52
    ፔ
    -1.52
    땃
    -1.48
    𓋼
    -1.46
    簟
    -1.45
    \}.
    -1.45
    ).$
    -1.44
    cepts
    -1.43
    POSITIVE LOGITS
     a
    1.93
     is
    1.68
     either
    1.50
     inoltre
    1.45
    </strong>
    1.43
     '',
    1.37
    </b>
    1.32
    萝
    1.32
     comunicar
    1.30
     dizaine
    1.29
    Activations Density 0.014%

    No Known Activations