© 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. 96635
    Prev
    Next
    INDEX
    Explanations

    conjunction "and"

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

    and not, and that, and they

    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
    ..(
    0.52
     conserver
    0.46
    𒋛
    0.44
     لم
    0.43
     문
    0.42
     광
    0.42
     Merkez
    0.42
     회
    0.42
     春
    0.41
     nascita
    0.41
    POSITIVE LOGITS
    chi
    0.47
    的這個
    0.46
     also
    0.45
    oin
    0.44
    ্যার
    0.43
    let
    0.43
     Andrews
    0.42
    iaan
    0.42
    ij
    0.42
    G
    0.42
    Activations Density 0.057%

    No Known Activations