© 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. 28899
    Prev
    Next
    INDEX
    Explanations

    Fun fact

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

    explains why or how

    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
    uk
    0.49
    uson
    0.47
    Worldwide
    0.45
    Web
    0.44
    leon
    0.43
    VISA
    0.43
    ma
    0.43
    ―
    0.43
    uks
    0.42
     Worldwide
    0.42
    POSITIVE LOGITS
     nirv
    0.50
     intermin
    0.50
     önemlidir
    0.50
     scrollBody
    0.50
     trữ
    0.49
     adecuadas
    0.48
     jedynie
    0.48
     kmeans
    0.48
     vuttam
    0.48
     ανθρώ
    0.48
    Activations Density 0.000%

    No Known Activations