© 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. 500
    Prev
    Next
    INDEX
    Explanations

    code, city, airport, former, gr, testing

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

    often brief

    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
     publicly
    0.50
     बधाई
    0.49
     prefixed
    0.49
     สํา
    0.48
     согласо
    0.48
     ደ
    0.47
    </h3>
    0.47
    、
    0.47
    ಂಡ
    0.47
     술
    0.47
    POSITIVE LOGITS
    Taste
    0.61
    া
    0.54
    Tasty
    0.51
    ান্ট
    0.50
    বায়
    0.50
    াং
    0.49
    یف
    0.48
    SEQU
    0.48
    Annotation
    0.48
    ান্দ
    0.47
    Activations Density 0.000%

    No Known Activations