© 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. 104338
    Prev
    Next
    INDEX
    Explanations

    mention and mint

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

    mentions and mint

    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
     проде
    0.51
     именно
    0.49
     Demonstrated
    0.48
     формата
    0.48
     fluctuations
    0.47
     приходится
    0.46
     п
    0.46
     атмос
    0.46
     ð
    0.45
     приме
    0.45
    POSITIVE LOGITS
    t
    0.63
    mint
    0.57
     mention
    0.56
    মেন্ট
    0.52
     mentoring
    0.52
    mention
    0.52
    ahmatullahi
    0.52
    veriş
    0.52
    tul
    0.49
    ról
    0.49
    Activations Density 0.036%

    No Known Activations