© 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. 247524
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    γα
    0.49
    lya
    0.47
     꺼
    0.45
    нето
    0.44
    ﺩ
    0.44
     accus
    0.43
     oggetto
    0.42
     hampers
    0.42
    筮
    0.42
     সংজ্ঞা
    0.42
    POSITIVE LOGITS
     Plane
    0.51
    Plane
    0.48
    ራት
    0.44
    etin
    0.44
     Прав
    0.44
     (),
    0.44
    aadhar
    0.44
     प्लानिंग
    0.43
     planned
    0.43
     Rotate
    0.43
    Activations Density 0.002%

    No Known Activations