© 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. 84509
    Prev
    Next
    INDEX
    Explanations

    is, years, one, us, continue, may

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

    odd numbers or dimensions

    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
    大切な
    0.52
    轍
    0.51
     ヴィ
    0.48
    uradaki
    0.46
    iters
    0.45
     границ
    0.43
     সূত্রের
    0.42
    長の
    0.42
    頚
    0.42
    xit
    0.42
    POSITIVE LOGITS
    теля
    0.64
    ály
    0.52
     at
    0.47
     each
    0.46
     by
    0.46
     aloud
    0.45
     thereto
    0.45
     to
    0.44
    ólito
    0.44
     only
    0.44
    Activations Density 0.001%

    No Known Activations