© 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. 223098
    Prev
    Next
    INDEX
    Explanations

    use maps

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

    customer support prompts

    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
    כל
    0.51
    alay
    0.47
    מות
    0.45
     Ster
    0.44
    צרים
    0.44
    🤽
    0.44
    螈
    0.43
    잍
    0.43
    眥
    0.43
     Superstar
    0.42
    POSITIVE LOGITS
    örungen
    0.47
     Aş
    0.47
     dàn
    0.44
    一群
    0.43
     dependant
    0.43
    ('+
    0.43
     কন্
    0.43
     প্রাথমিক
    0.42
    íp
    0.42
     grouped
    0.41
    Activations Density 0.000%

    No Known Activations