© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 1616
    Prev
    Next
    INDEX
    Explanations

    brand identity and messaging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
    ประโยชน์
    1.46
     trigonometry
    1.24
     correctement
    1.20
     μαγγ
    1.19
    JobID
    1.16
     bağlan
    1.15
    Reasoner
    1.15
    痰
    1.14
     preoperative
    1.12
     makalah
    1.11
    POSITIVE LOGITS
     menswear
    2.43
     Prada
    2.31
     boutiques
    2.26
     Gucci
    2.26
     handbags
    2.24
     catwalk
    2.22
     showrooms
    2.16
     Vogue
    2.12
     brands
    2.11
     streetwear
    2.11
    Activations Density 0.945%

    No Known Activations