© 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. 32842
    Prev
    Next
    INDEX
    Explanations

    multilingual technical terms

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

    not usually

    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
    ())).
    0.48
     सिद्धांत
    0.47
     Litigation
    0.47
    been
    0.46
    笥
    0.46
    divider
    0.45
    during
    0.45
     段
    0.45
    dictionary
    0.45
    nju
    0.45
    POSITIVE LOGITS
     integrada
    0.50
    மையில்
    0.46
     inglés
    0.46
     costru
    0.45
     proposé
    0.45
     inglês
    0.45
     italiane
    0.45
     terrestre
    0.45
     optimise
    0.44
     économiques
    0.44
    Activations Density 0.001%

    No Known Activations