© 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. 150768
    Prev
    Next
    INDEX
    Explanations

    The 39 Steps, Nova Scotia

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

    tropes and arms races

    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
    DO
    0.47
    */
    0.46
    ſt
    0.45
    बर्ग
    0.45
    ᾧ
    0.45
     FTSE
    0.45
     CHARLES
    0.44
    츈
    0.44
    δας
    0.44
    コ
    0.44
    POSITIVE LOGITS
     नियो
    0.47
     персона
    0.45
     இன்ற
    0.43
     düşünü
    0.43
     similarities
    0.42
     مشابه
    0.42
    leştir
    0.41
    zelfde
    0.41
     класс
    0.40
     مجموع
    0.40
    Activations Density 0.000%

    No Known Activations