© 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. 17540
    Prev
    Next
    INDEX
    Explanations

    origin or starting point

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

    origins and beginnings

    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
    로부터
    0.50
    сус
    0.45
     '-'
    0.45
    으로부터
    0.44
    乃至
    0.43
    posit
    0.43
    θούν
    0.42
    ;'
    0.40
     "-"
    0.39
    得到的
    0.39
    POSITIVE LOGITS
     weddings
    0.54
     earthquakes
    0.50
     تغيير
    0.47
     commemoration
    0.47
    ږئ
    0.45
     सुविधाजनक
    0.45
     heartbreak
    0.45
     governance
    0.44
     jumps
    0.44
     droughts
    0.44
    Activations Density 0.024%

    No Known Activations