© 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. 101760
    Prev
    Next
    INDEX
    Explanations

    weeks or months

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

    APIs, fleets, sarcastic

    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
    ುವುದ
    0.51
    ду
    0.51
    피
    0.50
    Фі
    0.49
    ፍተኛ
    0.49
    افر
    0.49
    iot
    0.47
    ádz
    0.47
    လေး
    0.47
    ТУ
    0.47
    POSITIVE LOGITS
     özellik
    0.49
     yönetim
    0.49
     eld
    0.48
     başta
    0.47
     ilk
    0.45
     baños
    0.45
     baat
    0.44
     l
    0.44
     eğer
    0.44
     ayr
    0.44
    Activations Density 0.000%

    No Known Activations