© 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. 6296
    Prev
    Next
    INDEX
    Explanations

    less or equal

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

    mathematics and formulas

    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
    dürü
    0.32
    otheby
    0.32
    ंगामा
    0.30
    ponsors
    0.29
    ően
    0.29
    ouncil
    0.28
    honneur
    0.28
    🏟
    0.28
    şehir
    0.28
    zechoslovak
    0.28
    POSITIVE LOGITS
     b
    0.34
     =
    0.32
     infinitesimal
    0.32
     {
    0.31
     polynomial
    0.31
     ∈
    0.31
     x
    0.30
     NULL
    0.29
    0
    0.29
     involution
    0.28
    Activations Density 0.039%

    No Known Activations