© 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. 72238
    Prev
    Next
    INDEX
    Explanations

    forum posts and threads

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

    lost things

    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
    ո
    0.48
     Aguilera
    0.47
    كره
    0.47
    ا
    0.47
    ظيم
    0.45
     Kategorie
    0.45
    اديم
    0.45
    可爱
    0.45
    satz
    0.44
    ه
    0.44
    POSITIVE LOGITS
    DS
    0.45
    PUS
    0.45
     телефон
    0.45
    atres
    0.44
    IST
    0.42
    PHP
    0.42
     PAPER
    0.42
    ERT
    0.41
    istas
    0.41
    asyarakat
    0.41
    Activations Density 0.002%

    No Known Activations