© 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. 128180
    Prev
    Next
    INDEX
    Explanations

    identification, mats, later, investment

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

    working, moisture, landlords, activities

    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
    ه
    0.46
    逈
    0.46
    陕
    0.45
    సం
    0.44
    تمر
    0.44
    ”（
    0.43
    وفر
    0.43
     כן
    0.43
    differ
    0.43
    گ
    0.42
    POSITIVE LOGITS
     unknowingly
    0.49
    ঞ্জেল
    0.49
     unwittingly
    0.47
     теорети
    0.46
     milliers
    0.46
     начиная
    0.45
     revest
    0.45
     понима
    0.43
     третий
    0.43
     understanding
    0.43
    Activations Density 0.001%

    No Known Activations