© 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. 19126
    Prev
    Next
    INDEX
    Explanations

    conjunctions and qualifiers

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

    each or every

    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
    blade
    0.44
    creative
    0.42
    lecture
    0.42
    는
    0.42
    唳
    0.41
     "'
    0.40
     창
    0.40
     manus
    0.40
    Daniel
    0.40
    discount
    0.40
    POSITIVE LOGITS
     россия
    0.50
     করণ
    0.49
     mỗi
    0.48
     everytime
    0.46
     ежеднев
    0.46
     кожен
    0.45
    誰
    0.45
     proguardFiles
    0.45
     hombres
    0.45
     Barriers
    0.45
    Activations Density 0.000%

    No Known Activations