© 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. 37225
    Prev
    Next
    INDEX
    Explanations

    showing treasures; what it/new; give a

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

    for frit, are easier, requires physically, understand dealing

    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
    {
    0.50
    0.50
     starred
    0.46
     miles
    0.45
     satisfe
    0.45
     snow
    0.44
    alls
    0.44
    r
    0.44
     acquire
    0.44
     expand
    0.44
    POSITIVE LOGITS
    셰
    0.50
     وهذه
    0.47
     때는
    0.46
     الجمع
    0.46
     Беларусь
    0.46
     griega
    0.46
     природных
    0.46
    에게
    0.43
    岖
    0.43
     Когда
    0.43
    Activations Density 0.000%

    No Known Activations