© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11730
    Prev
    Next
    INDEX
    Explanations

    purchasing an, entire year, view my

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

    following rules and expectations

    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_40_width_16k_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
    的な
    0.68
     हुए
    0.57
    いい
    0.57
    ن
    0.57
    裡的
    0.57
    た
    0.56
    ли
    0.55
     administrativas
    0.55
    လ
    0.54
    ני
    0.54
    POSITIVE LOGITS
    u
    0.69
    are
    0.59
    totally
    0.59
    upon
    0.55
    wrist
    0.55
    B
    0.55
    again
    0.54
    लिसिस
    0.54
    at
    0.54
    extremely
    0.54
    Activations Density 2.019%

    No Known Activations