© 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. 10111
    Prev
    Next
    INDEX
    Explanations

    otherwise followed by a verb

    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
    .
    -2.16
     it
    -2.09
     that
    -2.08
     “
    -2.08
     deberá
    -1.94
     to
    -1.88
    ৄ
    -1.82
     extremamente
    -1.80
     we
    -1.78
     cumple
    -1.76
    POSITIVE LOGITS
     lesquels
    2.16
     autorisation
    2.11
    इटम
    2.11
     erros
    2.09
    ｘ
    2.08
    梘
    2.03
    谂
    2.03
     februari
    2.02
    數字
    2.00
    ꩜
    1.99
    Activations Density 0.078%

    No Known Activations