© 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. 162756
    Prev
    Next
    INDEX
    Explanations

    Allow thewant themgroup cataloguepitch blacklove

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

    relation context or goals

    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
     hidup
    0.52
     as
    0.50
     dạng
    0.49
     semplic
    0.48
    脉
    0.47
    晉
    0.46
    Dalam
    0.46
    :
    0.46
    佺
    0.46
     caráter
    0.45
    POSITIVE LOGITS
     করেননি
    0.54
    存于互联网档案馆
    0.52
     foreshadow
    0.51
    nutrient
    0.50
     Yoshida
    0.46
    efficiency
    0.46
    ഹ്ലാദ
    0.46
    ニュ
    0.45
    cas
    0.45
    assembled
    0.45
    Activations Density 0.001%

    No Known Activations