© 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. 220023
    Prev
    Next
    INDEX
    Explanations

    regular tables, Christmas Welcome, provide a

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

    downloading and installing

    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
     gross
    0.46
    ного
    0.46
    ণ
    0.45
    ва
    0.45
     trường
    0.44
     stepwise
    0.43
     diminished
    0.42
     vân
    0.42
     hib
    0.42
    াও
    0.40
    POSITIVE LOGITS
     აქ
    0.49
     ხელისუფ
    0.48
     正規品
    0.48
     Ukraj
    0.47
     መሳሪያ
    0.46
    Ს
    0.46
     մ
    0.44
    დეს
    0.43
     해결
    0.43
     takim
    0.43
    Activations Density 0.002%

    No Known Activations