© 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. 218680
    Prev
    Next
    INDEX
    Explanations

    start with the rug

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

    if not

    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
    Altri
    0.50
     فرنسا
    0.50
    
    0.49
    Tonel
    0.49
    eliti
    0.47
     बनाएंगे
    0.46
    yse
    0.45
    ijken
    0.45
     علاج
    0.45
    一支
    0.45
    POSITIVE LOGITS
    ↵↵
    0.58
     Stop
    0.55
     of
    0.50
     Beef
    0.50
     nata
    0.49
     Phillips
    0.49
     (.)
    0.48
    )$,
    0.47
     ora
    0.47
    ATS
    0.46
    Activations Density 0.000%

    No Known Activations