© 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. 22-GEMMASCOPE-RES-131K
    7. 27857
    Prev
    Next
    INDEX
    Explanations

    question or phrase beginnings

    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_22/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
    </tfoot>
    -1.24
    ђа
    -1.20
    ###########
    -1.11
    ##########
    -1.10
    tempts
    -1.09
    providedIn
    -1.09
     vann
    -1.06
    🙌
    -1.05
     ordre
    -1.03
     lopp
    -1.00
    POSITIVE LOGITS
     soñar
    1.42
     decât
    1.18
     ahorrar
    1.18
     interactions
    1.17
    もあり
    1.16
     vuelve
    1.16
     tră
    1.15
     empêche
    1.15
     piatta
    1.13
     usarlo
    1.13
    Activations Density 0.000%

    No Known Activations