© 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. 7587
    Prev
    Next
    INDEX
    Explanations

    20 years

    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
    </em>
    -2.31
    </td>
    -2.17
    </h5>
    -1.96
    なども
    -1.95
    cartier
    -1.86
     */
    -1.85
    种族
    -1.84
     •
    -1.83
     secrete
    -1.80
    有序
    -1.78
    POSITIVE LOGITS
    9
    2.59
    8
    2.53
    3
    2.39
    0
    2.33
    7
    2.30
    𓆜
    2.17
    4
    2.08
    1
    1.91
    your
    1.83
    NUMX
    1.81
    Activations Density 0.085%

    No Known Activations