© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 192630
    Prev
    Next
    INDEX
    Explanations

    referring to themselves

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

    if they were

    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
    Negative Logits
    utiérrez
    0.52
    rivez
    0.50
    rello
    0.48
    ール
    0.47
    ulate
    0.47
    rl
    0.47
    izate
    0.47
    噫
    0.46
    ግራ
    0.46
    ífica
    0.46
    POSITIVE LOGITS
    s
    0.55
    e
    0.51
    َرَ
    0.48
     erf
    0.47
    AUR
    0.46
     z
    0.45
     ergonomics
    0.44
    ZEN
    0.44
     daniel
    0.44
    USING
    0.43
    Activations Density 0.001%

    No Known Activations