© 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. 66176
    Prev
    Next
    INDEX
    Explanations

    directions and positions

    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
    Elő
    -1.34
     réfléchir
    -1.22
    Jegy
    -1.18
    耵
    -1.18
    andte
    -1.18
    onews
    -1.17
    occurs
    -1.16
     konkret
    -1.14
     دلم
    -1.14
    now
    -1.12
    POSITIVE LOGITS
     usually
    1.29
     sometimes
    1.25
    <i>
    1.21
     often
    1.12
     zkou
    1.11
    <b>
    1.09
     немного
    1.09
     occasionally
    1.07
     sorta
    1.06
     когда
    1.05
    Activations Density 0.064%

    No Known Activations