© 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. 1304
    Prev
    Next
    INDEX
    Explanations

    commands and explanations

    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
     Kommun
    1.28
     Rück
    1.22
     gebo
    1.20
     tunneling
    1.19
    führer
    1.19
     Hrvatske
    1.18
    묶
    1.18
     artikel
    1.17
    kiye
    1.16
     Krankheit
    1.16
    POSITIVE LOGITS
    चंद
    1.51
    rivers
    1.50
    ‏
    1.50
    ன்ன
    1.48
    ராய
    1.48
    OD
    1.46
    rict
    1.46
    panel
    1.46
     nettement
    1.45
    ారు
    1.44
    Activations Density 0.000%

    No Known Activations