© 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. 146851
    Prev
    Next
    INDEX
    Explanations

    translation endpoint

    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
    ﺸ
    0.46
    ﺒ
    0.45
    慮
    0.44
    IÓN
    0.44
    撬
    0.43
    ición
    0.43
     переменную
    0.43
     Capacitor
    0.42
    밝
    0.42
     DARK
    0.42
    POSITIVE LOGITS
     slats
    0.49
    eng
    0.48
     Holdings
    0.48
     importa
    0.46
    el
    0.46
    ewords
    0.46
    ängel
    0.46
     outre
    0.44
     pellets
    0.44
    cony
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.