© 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. 2293
    Prev
    Next
    INDEX
    Explanations

    ssh commands and connections

    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
    ுமி
    1.38
     கூற
    1.36
    ുകൂ
    1.32
     prowess
    1.30
     macht
    1.28
     lig
    1.27
    ়
    1.25
    ér
    1.25
    opak
    1.25
    arli
    1.24
    POSITIVE LOGITS
     ["[
    2.00
    .".
    1.84
     Hear
    1.84
    Hear
    1.79
    饭
    1.77
     "\"
    1.74
    Neither
    1.70
     "\
    1.70
     "<
    1.69
     "`
    1.68
    Activations Density 0.006%

    No Known Activations