© 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. 112971
    Prev
    Next
    INDEX
    Explanations

    those who

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

    materials and science

    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
     Conta
    0.51
     DUI
    0.50
     GLOBAL
    0.47
     Tampa
    0.47
     lecture
    0.46
     grantee
    0.46
     ToString
    0.46
    ও
    0.46
     scene
    0.45
     Lecture
    0.45
    POSITIVE LOGITS
    д
    0.47
     أفضل
    0.47
    دأ
    0.45
    分別
    0.44
    ுடன்
    0.43
     сожа
    0.42
     அடு
    0.42
     incó
    0.42
     riddled
    0.42
    υ
    0.42
    Activations Density 0.001%

    No Known Activations