© 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. 190110
    Prev
    Next
    INDEX
    Explanations

    forward looking statements

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

    offering choices or specific details

    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
    小さな
    0.55
    わからない
    0.49
    ड़क
    0.49
    流れ
    0.48
    ພວກເຮ
    0.48
     Editable
    0.48
    쾅
    0.48
    rugated
    0.48
    同じ
    0.48
     સંબંધ
    0.47
    POSITIVE LOGITS
     distress
    0.49
     production
    0.44
     anlam
    0.43
     pharmacological
    0.42
     wetting
    0.42
    ){
    0.41
     palliative
    0.41
    K
    0.41
     raft
    0.41
     bans
    0.41
    Activations Density 0.001%

    No Known Activations