© 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. 234419
    Prev
    Next
    INDEX
    Explanations

    them/us followed by description

    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
    ของ
    0.68
    pictureBox
    0.66
    ofthe
    0.64
     ofthe
    0.63
     ofrec
    0.61
     e
    0.59
     nke
    0.59
     their
    0.59
    تهای
    0.59
    ຂອງ
    0.57
    POSITIVE LOGITS
    TERS
    0.65
    IAL
    0.64
    KEN
    0.62
    OLOGICAL
    0.59
    OCKET
    0.58
     ఐ
    0.58
    Gioco
    0.58
    ur
    0.57
     is
    0.56
    ين
    0.56
    Activations Density 0.044%

    No Known Activations