© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 104895
    Prev
    Next
    INDEX
    Explanations

    making love, against, primarily

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

    mathematical operations or questions

    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
     اروپا
    0.47
     phạm
    0.46
    欧洲
    0.43
     đất
    0.43
     ouro
    0.42
    tran
    0.42
    Z
    0.42
    Smoke
    0.42
     terre
    0.41
     پیش
    0.41
    POSITIVE LOGITS
    店家
    0.50
    increased
    0.49
     elektrische
    0.48
     AUGUST
    0.45
    ostomy
    0.45
    ᆯ
    0.45
     oste
    0.45
    ς
    0.45
    athed
    0.44
     คูณ
    0.44
    Activations Density 0.000%

    No Known Activations