© 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. 27413
    Prev
    Next
    INDEX
    Explanations

    celebrating new, source said, performed four

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

    allows or discusses states

    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
     നമ
    0.53
     Methoden
    0.50
     Vereinigten
    0.50
    厨
    0.49
    ভ্র
    0.48
     hervor
    0.48
     বিতর্ক
    0.48
    سطس
    0.48
    酭
    0.48
     базы
    0.48
    POSITIVE LOGITS
    performance
    0.50
     performance
    0.50
    stat
    0.47
     partner
    0.47
    s
    0.46
    cog
    0.44
    amiliar
    0.43
    െല്ലാം
    0.43
    esimo
    0.42
     over
    0.42
    Activations Density 0.000%

    No Known Activations