© 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. 118775
    Prev
    Next
    INDEX
    Explanations

    names and specific entities

    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
    ."
    -3.02
    떳
    -2.91
    r
    -2.69
    嫱
    -2.63
    ="
    -2.61
     das
    -2.59
    AL
    -2.52
    .</
    -2.48
    these
    -2.48
    </sup>
    -2.47
    POSITIVE LOGITS
     ständig
    2.36
     bemerkt
    2.31
     tirar
    2.28
     vestir
    2.25
     pensar
    2.25
     Penyakit
    2.20
     aktuellen
    2.19
     ولكن
    2.17
     dedicar
    2.17
     facilitar
    2.14
    Activations Density 0.059%

    No Known Activations