© 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. 173780
    Prev
    Next
    INDEX
    Explanations

    non-English words

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

    diverse languages and contexts

    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
    宇
    0.44
    بود
    0.43
    -----+
    0.42
    금
    0.41
    .
    0.41
     typed
    0.41
     PSP
    0.41
     progenitor
    0.41
     illuminated
    0.41
    占
    0.41
    POSITIVE LOGITS
     cheaply
    0.54
     ભાવ
    0.50
     চালানো
    0.47
     মনোভাব
    0.45
     ಸಾಧ್ಯ
    0.45
     ის
    0.43
     વાત
    0.42
     menggunakan
    0.42
    Categ
    0.42
    USING
    0.42
    Activations Density 0.000%

    No Known Activations