© 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. 23408
    Prev
    Next
    INDEX
    Explanations

    number and quantity phrases

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

    driving structural, product recommendation

    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
     boiled
    0.23
     Boots
    0.23
     skincare
    0.21
    ذاء
    0.21
     l
    0.20
     the
    0.20
    passed
    0.20
     Liquid
    0.20
     únicos
    0.20
     Titan
    0.20
    POSITIVE LOGITS
    墺
    0.29
    🎇
    0.28
     도형
    0.27
    мета
    0.26
     об
    0.26
     abhor
    0.26
     орке
    0.26
    achsen
    0.25
    ጐ
    0.25
     иных
    0.25
    Activations Density 0.111%

    No Known Activations