© 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. 37227
    Prev
    Next
    INDEX
    Explanations

    thumbs up/down signals

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

    juxtaposition

    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
     expedi
    0.40
     사고
    0.39
     underwriting
    0.38
     رولی
    0.38
    뽁
    0.38
     Troubleshooting
    0.37
     مرح
    0.36
     حادث
    0.35
     párrafo
    0.35
    렴
    0.34
    POSITIVE LOGITS
     次元
    0.42
     Ign
    0.41
     Для
    0.41
     भीम
    0.40
    жь
    0.40
     ignored
    0.40
     画像
    0.40
    人間の
    0.40
    ήμε
    0.39
     Auro
    0.39
    Activations Density 0.000%

    No Known Activations