© 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. 80978
    Prev
    Next
    INDEX
    Explanations

    "This luxury", "know why", "tx simple", "reading to", "Vegan Cheese"

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

    short phrases or descriptions

    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
    s
    0.51
    Graphical
    0.49
    tac
    0.49
     graphically
    0.48
          
    0.47
    sch
    0.47
    س
    0.47
    Coca
    0.47
    ي
    0.47
    Cock
    0.46
    POSITIVE LOGITS
    ূতন
    0.45
     spineItem
    0.45
    ками
    0.44
     ▸
    0.44
     டிகிரி
    0.44
     Seung
    0.42
    itochond
    0.41
     samurai
    0.41
     растение
    0.41
     jati
    0.40
    Activations Density 0.000%

    No Known Activations