© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 15069
    Prev
    Next
    INDEX
    Explanations

    river, Nile, waterfall

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cellulaire
    0.55
    膻
    0.48
     ஈடுபட்ட
    0.48
    鹛
    0.47
    proguard
    0.47
     cancé
    0.47
     গাড়ীতে
    0.46
     postdoc
    0.46
    蔷
    0.46
    ruzzo
    0.46
    POSITIVE LOGITS
     river
    1.94
     River
    1.54
    River
    1.48
    river
    1.45
     नदी
    1.42
    河
    1.38
     rivers
    1.36
     RIVER
    1.34
     fiume
    1.32
     নদীর
    1.23
    Activations Density 0.108%

    No Known Activations