© 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. 153515
    Prev
    Next
    INDEX
    Explanations

    official or legal contexts

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

    factual statements and definitions

    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
     на
    0.55
     про
    0.55
     от
    0.54
     пор
    0.53
     сом
    0.52
     increases
    0.52
     перед
    0.52
     ή
    0.51
     equations
    0.50
     Перед
    0.49
    POSITIVE LOGITS
    اولة
    0.43
     benutzer
    0.42
     이러
    0.40
    Mak
    0.40
     mittler
    0.39
    ANZ
    0.39
    تبقى
    0.39
    דיה
    0.38
    نده
    0.38
    ลีก
    0.38
    Activations Density 0.000%

    No Known Activations