© 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. 17979
    Prev
    Next
    INDEX
    Explanations

    pronouns and auxiliary verbs

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

    U-speak, Pig Latin, foreign languages

    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
     .(
    0.30
    .?
    0.29
     annihilation
    0.29
    .!
    0.29
    .³
    0.28
     alertDialog
    0.28
    ..(
    0.28
     ?.
    0.28
     ..
    0.27
    .??
    0.27
    POSITIVE LOGITS
    i
    0.33
    e
    0.30
    atividade
    0.27
    existe
    0.25
    a
    0.25
    етки
    0.25
    Beth
    0.24
    ἢ
    0.24
    έρα
    0.24
    Է
    0.24
    Activations Density 0.732%

    No Known Activations