© 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. 7-GEMMASCOPE-2-RES-16K
    7. 1297
    Prev
    Next
    INDEX
    Explanations

    reduce or lower

    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
    instellung
    2.21
     berbah
    2.20
     menutup
    2.16
    버
    2.15
    ິງ
    2.13
    챠
    2.11
     tubuh
    2.09
    ختی
    2.09
     wajah
    2.07
     sebi
    2.04
    POSITIVE LOGITS
     down
    2.59
    Down
    2.42
     $(<
    2.34
     Down
    2.26
    ϊ
    2.23
    down
    2.20
    成本
    2.20
    es
    2.15
    俗
    2.09
    salir
    2.08
    Activations Density 1.267%

    No Known Activations