© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2424
    Prev
    Next
    INDEX
    Explanations

    company or technical names

    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_65k_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
    Tính
    1.43
    𝙵
    1.26
    स्पर
    1.25
    avkh
    1.24
     हैव
    1.23
    Hình
    1.22
     Heterocycl
    1.22
    См
    1.22
    Какой
    1.22
    Arkadaşlar
    1.21
    POSITIVE LOGITS
     Productions
    1.85
    ™,
    1.85
    ™
    1.81
    ™.
    1.73
    ®,
    1.66
    ®.
    1.55
     Ltd
    1.54
    ®
    1.48
     Academy
    1.35
     workshop
    1.35
    Activations Density 2.210%

    No Known Activations