© 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. 916
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    णाची
    1.26
    cemos
    1.17
     একটা
    1.17
     спокой
    1.16
     कोई
    1.15
    相应的
    1.14
     ilość
    1.11
    沇
    1.11
     puedan
    1.11
    ፈላጊ
    1.10
    POSITIVE LOGITS
     which
    1.21
     unveiled
    1.20
     launched
    1.15
     of
    1.14
     that
    1.13
     nicknamed
    1.11
     spearheaded
    1.11
     debacle
    1.11
    which
    1.11
     alongside
    1.10
    Activations Density 1.243%

    No Known Activations