© 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. 195382
    Prev
    Next
    INDEX
    Explanations

    has, have

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

    individual variation

    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
     m
    0.57
    ’
    0.55
     occidental
    0.54
     R
    0.53
    asp
    0.53
     n
    0.52
    4
    0.52
    umin
    0.52
    :
    0.52
     minute
    0.51
    POSITIVE LOGITS
    体
    0.52
    त्तियों
    0.52
    迟
    0.52
    ρύ
    0.52
    partitions
    0.51
    ⚤
    0.51
    ৎস্য
    0.51
    ніше
    0.50
    linetype
    0.49
    ানিতে
    0.49
    Activations Density 0.001%

    No Known Activations