© 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. 95938
    Prev
    Next
    INDEX
    Explanations

    region such as

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

    technical, scientific, and foreign language content

    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
    ோர
    0.47
     रोजी
    0.43
    íte
    0.43
    cumin
    0.43
     Söz
    0.43
    erode
    0.42
     handwritten
    0.42
    ṣ
    0.42
     serem
    0.41
     Yin
    0.40
    POSITIVE LOGITS
    ని
    0.51
     ਗਿਆ
    0.50
    ក្រោយ
    0.46
     ಪ್ಯಾ
    0.45
    ни
    0.44
     nuis
    0.43
    嫨
    0.43
    WINDOW
    0.42
     foreclose
    0.42
     TECH
    0.42
    Activations Density 0.000%

    No Known Activations