© 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. 22901
    Prev
    Next
    INDEX
    Explanations

    percentage comparisons

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

    comparison between items

    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
     damal
    0.42
    ḏ
    0.42
     slightest
    0.41
     消
    0.41
    lisi
    0.40
    (−
    0.39
     ②
    0.39
    )】
    0.39
    )*(
    0.39
    ູບ
    0.38
    POSITIVE LOGITS
     Substance
    0.41
     зарубе
    0.41
     Foster
    0.40
     proté
    0.40
    UserDefaults
    0.40
    ẹt
    0.40
    Ꮏ
    0.40
     subtypes
    0.39
    طلاب
    0.39
     विदेशों
    0.39
    Activations Density 0.014%

    No Known Activations