© 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. 129050
    Prev
    Next
    INDEX
    Explanations

    descriptive words followed by nouns

    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
     consci
    -1.38
    Restrict
    -1.24
     afect
    -1.23
     encor
    -1.23
    öm
    -1.23
     seis
    -1.23
     saud
    -1.20
     -
    -1.20
     captur
    -1.20
     afront
    -1.19
    POSITIVE LOGITS
    nitř
    1.65
     aktiviteter
    1.54
     aktivitet
    1.40
     باشی
    1.38
    0
    1.38
    iation
    1.35
     stål
    1.34
     requieren
    1.32
     erwäh
    1.30
     urodz
    1.29
    Activations Density 0.108%

    No Known Activations