© 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. 158904
    Prev
    Next
    INDEX
    Explanations

    honored, stimulate, feeling, aspects

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

    specific entities and states

    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
     ም
    0.55
     ସ
    0.51
     любят
    0.51
     ബെ
    0.50
     имат
    0.49
     បាន
    0.49
     すご
    0.49
     любит
    0.48
     હ
    0.48
     Фонбет
    0.48
    POSITIVE LOGITS
     (
    0.55
     [
    0.47
     —
    0.46
     specified
    0.46
     specifying
    0.46
     Etr
    0.45
     Double
    0.44
    ที่คุณ
    0.44
    ↵
    0.43
     maîtres
    0.43
    Activations Density 0.001%

    No Known Activations