© 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. 95541
    Prev
    Next
    INDEX
    Explanations

    grades, commendations

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

    word followed by "the" or "a"

    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
    દાર
    0.57
     Đầu
    0.55
     periodista
    0.52
     shang
    0.50
     seç
    0.49
     usługi
    0.49
     साइनस
    0.49
     "*");
    0.49
     Vysok
    0.48
     පෙර
    0.47
    POSITIVE LOGITS
    Day
    0.46
    prised
    0.45
    loos
    0.45
    '
    0.44
    ul
    0.44
    grads
    0.44
    grades
    0.43
    commended
    0.43
    grader
    0.43
    reg
    0.43
    Activations Density 0.000%

    No Known Activations