© 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. 169414
    Prev
    Next
    INDEX
    Explanations

    articles and prepositions

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

    steps or instructions

    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
    ↵
    0.55
     set
    0.55
     commodity
    0.53
     hard
    0.51
    c
    0.51
     detective
    0.50
     legislative
    0.50
     working
    0.49
     Westfield
    0.49
     heat
    0.49
    POSITIVE LOGITS
    
    0.54
     }{}_{\
    0.53
    бран
    0.50
     захворю
    0.50
    的最大
    0.49
    érieur
    0.49
     unités
    0.49
     стандарта
    0.48
    ्या
    0.47
    älfte
    0.47
    Activations Density 0.000%

    No Known Activations