© 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. 159989
    Prev
    Next
    INDEX
    Explanations

    six animals, passengers, reviewed, similar, enact, child, production, germ

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

    achieving goals or objectives

    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
     renfer
    0.54
    ;";
    0.52
     fournis
    0.50
    པ་
    0.50
    ;"
    0.50
     essentielles
    0.49
    ﺔ
    0.49
     appartenant
    0.48
    anterie
    0.47
     obtenu
    0.46
    POSITIVE LOGITS
     NOK
    0.52
     whack
    0.48
     Wend
    0.46
     ISA
    0.46
     until
    0.46
     Dub
    0.46
     Á
    0.45
     Isa
    0.45
     Venn
    0.44
     Att
    0.44
    Activations Density 0.001%

    No Known Activations