© 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. 6068
    Prev
    Next
    INDEX
    Explanations

    This Classic, Beautiful

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

    polite and formal phrasing

    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
     prots
    0.36
    CodeGen
    0.33
    4
    0.32
     数据
    0.31
    ō
    0.31
     collaborazione
    0.31
     সহায়তা
    0.30
    0
    0.30
    grads
    0.30
     cùng
    0.30
    POSITIVE LOGITS
    {
    0.35
     politely
    0.32
    ເພດ
    0.31
     justiciable
    0.31
     predeceased
    0.30
     insinu
    0.30
    allaitement
    0.29
     leyendo
    0.29
    помним
    0.29
     hurtful
    0.29
    Activations Density 0.301%

    No Known Activations