© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 191476
    Prev
    Next
    INDEX
    Explanations

    physical commodities

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

    synonyms for

    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
    АСС
    0.58
    犠
    0.49
     baseless
    0.48
    நிதி
    0.48
    EFI
    0.47
     கிட்டத்தட்ட
    0.46
     tokom
    0.45
    щает
    0.45
     kész
    0.45
     prerequisite
    0.45
    POSITIVE LOGITS
     говори
    0.46
    전
    0.46
    ait
    0.45
    arn
    0.44
    atur
    0.44
    uten
    0.43
    atis
    0.43
    ati
    0.43
    iten
    0.43
    iva
    0.43
    Activations Density 0.001%

    No Known Activations