© 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. 234621
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

    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
    пански
    0.53
    ("|"+"
    0.52
     INKA
    0.49
     ilan
    0.49
    ార్క్
    0.49
     Abyss
    0.47
    Antae
    0.45
     स्नेह
    0.45
     provisional
    0.45
     pj
    0.45
    POSITIVE LOGITS
    ajú
    0.57
    č
    0.50
    eper
    0.49
    élect
    0.48
    𝐨
    0.48
    ključ
    0.47
    aju
    0.46
    ipi
    0.46
    𝐚
    0.46
    ت
    0.46
    Activations Density 0.001%

    No Known Activations