© 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. 7951
    Prev
    Next
    INDEX
    Explanations

    common word continuations

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

    explaining complex topics

    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
    \}$.
    0.31
     বরাদ্দ
    0.27
     initialized
    0.27
     گئی۔
    0.27
    SENSOR
    0.26
     brillo
    0.26
    স্পতিবার
    0.26
     Initialization
    0.26
    ক্কা
    0.25
     আশ্বাস
    0.25
    POSITIVE LOGITS
    itus
    0.26
    ău
    0.26
    -​
    0.25
    Ort
    0.25
     Гор
    0.25
     세상
    0.25
    ân
    0.25
     Мер
    0.24
    atar
    0.24
    adel
    0.24
    Activations Density 1.029%

    No Known Activations