© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 194260
    Prev
    Next
    INDEX
    Explanations

    objects and qualities

    np_acts-logits-general · gemini-2.5-flash-lite

    Barnaby

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     பிறகு
    0.52
     permitió
    0.50
     позволи
    0.50
     jų
    0.48
     pozwala
    0.48
    娩
    0.48
     imprese
    0.48
     progen
    0.48
    その後
    0.48
     beers
    0.47
    POSITIVE LOGITS
    лександр
    0.44
     KIND
    0.43
    о
    0.42
    του
    0.41
    никова
    0.40
    ffected
    0.40
     кого
    0.40
     SCIENCE
    0.40
    촤
    0.40
     bulge
    0.39
    Activations Density 0.006%

    No Known Activations