© 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. 175534
    Prev
    Next
    INDEX
    Explanations

    many things, systems, element

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

    carousel post generation

    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
    improve
    0.61
    サ
    0.61
    improvement
    0.55
    ഇ
    0.54
    اسي
    0.52
     as
    0.51
     improvement
    0.50
    അ
    0.49
     axioms
    0.49
     sacked
    0.48
    POSITIVE LOGITS
     منطقه
    0.49
     Lieber
    0.48
     Sommer
    0.47
     옳은
    0.45
    絊
    0.45
     حاج
    0.45
     Narrative
    0.44
     escoger
    0.44
     titer
    0.44
     खासा
    0.42
    Activations Density 0.000%

    No Known Activations