© 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. 70962
    Prev
    Next
    INDEX
    Explanations

    X of Y

    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
    ).
    -2.11
    ].
    -1.98
    .“
    -1.97
     which
    -1.95
     indicating
    -1.84
    </em>
    -1.83
     sehr
    -1.80
    л
    -1.80
    .
    -1.80
    ."
    -1.79
    POSITIVE LOGITS
    鶺
    2.20
     deliciously
    2.11
    硨
    1.98
     progrès
    1.88
    ková
    1.83
     rapidement
    1.79
     bloquer
    1.74
    快要
    1.74
    嗫
    1.74
    釹
    1.73
    Activations Density 0.284%

    No Known Activations