© 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. 6060
    Prev
    Next
    INDEX
    Explanations

    less, fewer, thinner, better

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

    less or more comparison

    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
    আই
    0.39
    とても
    0.39
     انتہائی
    0.38
    ή
    0.38
     ஐந்து
    0.37
    यूपी
    0.37
    ですし
    0.36
    임을
    0.36
    ஐ
    0.36
     ENGINEERING
    0.35
    POSITIVE LOGITS
     less
    0.82
     훨씬
    0.70
     weniger
    0.70
     menos
    0.69
     гораздо
    0.69
     fewer
    0.69
     mindre
    0.68
     moins
    0.68
     менее
    0.66
     hingegen
    0.62
    Activations Density 0.314%

    No Known Activations