© 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. 47366
    Prev
    Next
    INDEX
    Explanations

    instructions for preparation

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

    capability assessment

    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
     車
    0.54
     开
    0.54
     書き
    0.52
    これまで
    0.50
    騎士
    0.50
     গিয়াছেন
    0.50
    विधि
    0.49
    nonatomic
    0.49
     多く
    0.48
    骑士
    0.47
    POSITIVE LOGITS
     Ebene
    0.52
     inaccur
    0.52
     obsess
    0.47
     Irland
    0.47
    ,
    0.45
     énorme
    0.45
     attract
    0.45
     acontecer
    0.45
     lokal
    0.44
     Imran
    0.44
    Activations Density 0.000%

    No Known Activations