© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 48019
    Prev
    Next
    INDEX
    Explanations

    more adjective

    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
    行為
    -1.42
    </b>
    -1.41
     обратить
    -1.38
    上記
    -1.37
     vidrio
    -1.36
     slechts
    -1.36
     beve
    -1.33
     every
    -1.31
    osamente
    -1.30
     comprando
    -1.29
    POSITIVE LOGITS
     than
    1.66
     of
    1.59
     []:
    1.57
    {~
    1.45
     miei
    1.45
    ôgrafia
    1.44
     things
    1.42
     dowol
    1.41
     circumvent
    1.40
     –
    1.39
    Activations Density 0.015%

    No Known Activations