© 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. 43350
    Prev
    Next
    INDEX
    Explanations

    between your, lucky number, out for, in those, completing an

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

    veterinary medicine or player

    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
     Khi
    0.49
     кухни
    0.48
     Ketika
    0.48
    approve
    0.47
     dilute
    0.47
    鑾
    0.46
     khi
    0.46
    Khi
    0.46
     acepta
    0.45
     Cuando
    0.43
    POSITIVE LOGITS
     싫
    0.47
     shattering
    0.47
     shamb
    0.46
     پوس
    0.41
    !;
    0.41
    shed
    0.40
    🫂
    0.40
     dreadful
    0.40
    ၈
    0.40
    collision
    0.40
    Activations Density 0.000%

    No Known Activations