© 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. 206419
    Prev
    Next
    INDEX
    Explanations

    small intestine

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

    Old Man Tiber's sketching

    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
    弑
    0.53
    的世界
    0.50
    啻
    0.47
     миро
    0.47
     Sebagai
    0.46
    ัฒ
    0.46
    ર
    0.45
    राष्ट
    0.45
     ツ
    0.45
    トル
    0.45
    POSITIVE LOGITS
     Mathematics
    0.46
     maths
    0.46
     both
    0.45
     እና
    0.44
     schrift
    0.44
     BOTH
    0.43
     mathematicians
    0.42
     أيضًا
    0.42
     matemática
    0.41
     både
    0.41
    Activations Density 0.001%

    No Known Activations