© 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. 137779
    Prev
    Next
    INDEX
    Explanations

    sentence endings or continuations

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

    personal projects

    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
    ेट
    0.54
    ᖁ
    0.52
    метров
    0.52
    कोट
    0.51
     amelyet
    0.51
     penjumlahan
    0.51
     obiettivo
    0.51
    ڑ
    0.51
     kemampuan
    0.51
    ᒻ
    0.51
    POSITIVE LOGITS
    OG
    0.53
    elle
    0.50
    ils
    0.49
    ">
    0.49
    yl
    0.48
    istar
    0.47
    star
    0.46
    itar
    0.46
    renew
    0.46
    </span>
    0.46
    Activations Density 0.001%

    No Known Activations