© 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. 7-GEMMASCOPE-2-RES-16K
    7. 1739
    Prev
    Next
    INDEX
    Explanations

    news publications

    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_7_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
    신도시
    2.33
    赟
    2.31
     elegans
    2.27
    ipeline
    2.26
    ec
    2.24
     multer
    2.21
    جاز
    2.19
    Einzelnachweise
    2.17
    ɦ
    2.16
    axies
    2.16
    POSITIVE LOGITS
    determ
    2.43
    䜣
    2.35
    }$)
    2.33
     perils
    2.29
    দূর
    2.27
     DETER
    2.19
    跟他
    2.19
    𝗬
    2.19
    iguez
    2.17
    сь
    2.15
    Activations Density 0.031%

    No Known Activations