© 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. 54546
    Prev
    Next
    INDEX
    Explanations

    any other

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

    -ism words and capitalism

    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
    ();//
    0.49
    损伤
    0.49
     acides
    0.49
    ائية
    0.48
    章节
    0.47
    ିକ
    0.47
     itinéraires
    0.47
    descr
    0.46
    سب
    0.45
     வளர்ச்சி
    0.45
    POSITIVE LOGITS
    heri
    0.54
    a
    0.49
     RNA
    0.47
     Redd
    0.47
    esh
    0.46
     Nielsen
    0.46
     remake
    0.45
     RPG
    0.44
     tripartite
    0.44
     Parker
    0.44
    Activations Density 0.000%

    No Known Activations