© 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. 43639
    Prev
    Next
    INDEX
    Explanations

    characteristic of specific features

    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
    螣
    -1.63
    ."
    -1.51
    ubah
    -1.42
    取る
    -1.42
    homology
    -1.41
    </strong>
    -1.38
    
    -1.38
    ıld
    -1.38
    还想
    -1.36
     săn
    -1.34
    POSITIVE LOGITS
     Characteristic
    1.71
     characteristic
    1.71
    Харак
    1.59
     that
    1.55
    in
    1.44
     jahre
    1.43
    Interestingly
    1.41
    at
    1.38
    Characteristic
    1.38
     sebagaimana
    1.30
    Activations Density 0.039%

    No Known Activations