© 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. 249300
    Prev
    Next
    INDEX
    Explanations

    is a, and, unless, she, techno, client

    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
    ö
    0.50
    ore
    0.49
    icks
    0.48
    äs
    0.48
    is
    0.47
    í
    0.47
     resulted
    0.47
     became
    0.46
    became
    0.45
    é
    0.45
    POSITIVE LOGITS
     آینده
    0.49
     profiter
    0.49
     cadeaux
    0.49
     буду
    0.48
     এখনই
    0.48
     Sekarang
    0.48
     budou
    0.46
    Semester
    0.46
    طفال
    0.45
     toekomst
    0.45
    Activations Density 0.003%

    No Known Activations