© 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. 149297
    Prev
    Next
    INDEX
    Explanations

    dates, or might, during, at, still

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

    chest, contain, tied, tree

    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
    های
    0.57
    ުގެ
    0.55
    هاي
    0.55
    دهای
    0.54
    ۶
    0.54
    ٩
    0.54
    ٧
    0.52
     Акы
    0.52
     रात
    0.52
    வைப்
    0.52
    POSITIVE LOGITS
    0.49
     Civ
    0.48
     gross
    0.47
     Label
    0.47
     Input
    0.46
     Attempt
    0.46
     are
    0.44
     shorten
    0.44
    inci
    0.44
     Placement
    0.43
    Activations Density 0.001%

    No Known Activations