© 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. 59190
    Prev
    Next
    INDEX
    Explanations

    same, real, moment

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

    consistent results or stability

    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
     آم
    0.52
    ヴ
    0.45
     Finlandia
    0.45
    punkt
    0.44
     TimeUnit
    0.44
    Profiling
    0.44
     Handels
    0.43
     войне
    0.43
     অপু
    0.43
     Sexuality
    0.42
    POSITIVE LOGITS
    o
    0.52
    i
    0.49
    ன
    0.47
    主要
    0.44
    ராஜ்
    0.44
    ;
    0.43
    确定
    0.42
    DAD
    0.42
    好了
    0.42
    ه
    0.42
    Activations Density 0.000%

    No Known Activations