© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22342
    Prev
    Next
    INDEX
    Explanations

    expressing opinions or observations

    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
    </em>
    -1.26
    䊐
    -1.22
    袿
    -1.17
    sü
    -1.16
    9
    -1.16
    ቍ
    -1.16
    stricken
    -1.14
    ėja
    -1.13
    جون
    -1.12
     any
    -1.11
    POSITIVE LOGITS
     canad
    1.25
     corred
    1.20
     from
    1.17
    はこんな感じ
    1.12
    ومة
    1.10
    亿美元
    1.10
    t
    1.10
     through
    1.08
     europa
    1.07
     nicknamed
    1.06
    Activations Density 0.249%

    No Known Activations