© 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. 151706
    Prev
    Next
    INDEX
    Explanations

    affiliate, property, or sequence

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

    directions, attacker, sat, alternative, ground, learned, activities, locations

    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
     تغ
    0.46
    
    0.46
     Grundlagen
    0.43
     Negra
    0.41
     stvari
    0.39
     வழங்கு
    0.39
     españoles
    0.39
     arşiv
    0.37
     Gesù
    0.37
     rendus
    0.37
    POSITIVE LOGITS
    tribe
    0.43
     amide
    0.42
    untitled
    0.41
     unnamed
    0.41
    한다고
    0.40
    竽
    0.40
    trib
    0.40
     utensil
    0.40
     neodymium
    0.40
    称为
    0.40
    Activations Density 0.002%

    No Known Activations