© 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. 203991
    Prev
    Next
    INDEX
    Explanations

    square shape

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

    academic applications

    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
     Nasional
    0.48
     n
    0.47
     Nottingham
    0.45
     Latinos
    0.44
     Gaza
    0.43
     ostr
    0.43
     devast
    0.43
     oscuridad
    0.43
     دست
    0.42
     Brandt
    0.42
    POSITIVE LOGITS
    เท
    0.54
    יי
    0.48
    尻
    0.48
    頂
    0.48
    噹
    0.48
    んじゃない
    0.47
    ActionListener
    0.47
    antwoord
    0.46
    কাতা
    0.45
    ิจ
    0.45
    Activations Density 0.001%

    No Known Activations