© 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. 181030
    Prev
    Next
    INDEX
    Explanations

    medical issues and legislation

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

    unprecedented precision, comprehensive overview

    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
    须
    0.46
    Camp
    0.45
    Kyle
    0.42
     the
    0.41
    The
    0.41
    ED
    0.41
    Perm
    0.41
    ＆
    0.41
     Camp
    0.40
    UO
    0.40
    POSITIVE LOGITS
     sobretudo
    0.47
     hjæl
    0.47
    ヴ
    0.47
     やつ
    0.46
     dvije
    0.45
    imcoords
    0.44
     helfen
    0.44
     rhizosphere
    0.44
     noin
    0.44
     ingred
    0.43
    Activations Density 0.000%

    No Known Activations