© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7115
    Prev
    Next
    INDEX
    Explanations

    marketing and advertising concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    𝘂
    2.66
    𝘄
    2.63
    𝗳
    2.57
    უფ
    2.27
    𝐟
    2.24
    𝐰
    2.23
    𝓬
    2.23
    𝐮
    2.22
    𝓶
    2.21
    чко
    2.21
    POSITIVE LOGITS
    isements
    2.64
    ጀመሪያ
    2.48
    げ
    2.46
     می‌توان
    2.45
     Hoc
    2.39
     خور
    2.30
     hoc
    2.27
    ھی
    2.24
     isk
    2.22
    뭣
    2.21
    Activations Density 0.945%

    No Known Activations