© 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. 241933
    Prev
    Next
    INDEX
    Explanations

    average quantities and manner

    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
     ৃ
    0.57
    \\'
    0.50
    }}=\
    0.50
    Md
    0.45
     შ
    0.45
     如果
    0.43
     отмеча
    0.42
    谢
    0.42
    Chips
    0.42
    ఙ
    0.42
    POSITIVE LOGITS
    िक
    0.66
    ψε
    0.51
     trusts
    0.49
    भद्र
    0.45
     entwickelte
    0.45
    انی
    0.45
    สาม
    0.45
    ψ
    0.44
    ویان
    0.44
    轭
    0.44
    Activations Density 0.001%

    No Known Activations