© 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. 157096
    Prev
    Next
    INDEX
    Explanations

    buttermilk onion rings

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

    heavy accommodations

    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
     hoàn
    0.49
     vidrio
    0.48
     технологи
    0.48
    駑
    0.47
    naph
    0.46
     vẫn
    0.45
     ремонта
    0.45
    '_{\
    0.45
     कर्मचारी
    0.44
    setMax
    0.44
    POSITIVE LOGITS
     individuality
    0.48
     transcendent
    0.45
     bookshelf
    0.45
     solitude
    0.44
     situés
    0.44
     otherworldly
    0.44
     Alger
    0.43
     ennemis
    0.43
    ښ
    0.42
     subjectivity
    0.42
    Activations Density 0.001%

    No Known Activations