© 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. 43360
    Prev
    Next
    INDEX
    Explanations

    advent of new eras

    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
    </h5>
    -1.81
     dieťa
    -1.40
    旛
    -1.38
     lèvres
    -1.38
    </h3>
    -1.36
     związ
    -1.34
    okości
    -1.32
     mêmes
    -1.31
     badkamer
    -1.30
     */
    -1.29
    POSITIVE LOGITS
     polícia
    1.45
    黩
    1.45
    ,“
    1.43
    .
    1.42
     his
    1.41
     {};
    1.41
     their
    1.41
     to
    1.38
     nij
    1.38
    </>
    1.37
    Activations Density 0.100%

    No Known Activations