© 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. 53946
    Prev
    Next
    INDEX
    Explanations

    icons, masterpieces, gems, stars

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

    masterpiece, legend, gem, institution

    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
    as
    0.83
    q
    0.75
    u
    0.72
    is
    0.72
    бо
    0.71
    en
    0.71
    é
    0.71
    ع
    0.69
    و
    0.67
    o
    0.66
    POSITIVE LOGITS
     unleash
    0.64
     unfold
    0.62
    খ্যাত
    0.61
     adore
    0.61
     collide
    0.59
     assemble
    0.57
    𝗥
    0.56
     exclude
    0.55
     單
    0.55
     explode
    0.54
    Activations Density 0.091%

    No Known Activations