© 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. 77816
    Prev
    Next
    INDEX
    Explanations

    events and conditions

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

    eliminating needs

    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
    ны
    0.43
     เงี้ย
    0.43
     supernova
    0.41
    卑
    0.40
    agam
    0.40
    ab
    0.40
    柾
    0.39
    φα
    0.39
     gunfire
    0.38
     στρα
    0.38
    POSITIVE LOGITS
    spunkt
    0.55
     Schwier
    0.53
     poziom
    0.53
     wasser
    0.52
    する
    0.50
    punkt
    0.50
    स्थल
    0.49
     alertness
    0.48
     Bhos
    0.48
     ഏറ്റ
    0.47
    Activations Density 0.000%

    No Known Activations