© 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. 157529
    Prev
    Next
    INDEX
    Explanations

    above. typically happens. rate fell. based on

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

    value experiences introspective generally

    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
     হ্
    0.52
     റേ
    0.48
     autonomía
    0.46
    Lähteet
    0.46
    orsz
    0.45
     AdWords
    0.45
     Frankreich
    0.45
     *\
    0.45
     templateUrl
    0.42
     Technik
    0.42
    POSITIVE LOGITS
    with
    0.51
    निम्
    0.44
    claimer
    0.44
     דו
    0.43
    farande
    0.43
     पाहिजे
    0.43
    บริษัท
    0.42
    do
    0.42
    日は
    0.42
    公司
    0.42
    Activations Density 0.001%

    No Known Activations