© 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. 54575
    Prev
    Next
    INDEX
    Explanations

    GOP, trash, generated funds, common, forceps

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

    different languages for "or"

    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
    டிக்க
    0.47
    BOUR
    0.47
    ◸
    0.47
     remarkably
    0.46
     strikingly
    0.46
    汎
    0.46
    темати
    0.45
    يهم
    0.45
    Entrepreneur
    0.44
    же
    0.43
    POSITIVE LOGITS
     eller
    0.53
     หรือ
    0.52
     ถ
    0.50
     αντί
    0.48
     violations
    0.48
     protocols
    0.46
     जीएस
    0.46
     ช่อง
    0.46
     annen
    0.45
     kuning
    0.45
    Activations Density 0.000%

    No Known Activations