© 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. 251665
    Prev
    Next
    INDEX
    Explanations

    knowing what

    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
    萨
    0.58
    טר
    0.53
     richi
    0.47
    샹
    0.46
    霍
    0.46
    рем
    0.44
    柯
    0.44
    薩
    0.44
    ቮ
    0.43
     ಭೂ
    0.43
    POSITIVE LOGITS
     Quran
    0.50
     Degree
    0.49
     System
    0.46
     MTT
    0.45
     GPs
    0.45
     BBQ
    0.45
     OI
    0.45
     IRB
    0.44
     roster
    0.44
     Puebla
    0.44
    Activations Density 0.000%

    No Known Activations