© 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. 2020
    Prev
    Next
    INDEX
    Explanations

    even more suggestions

    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
    1
    2.36
    0
    2.27
    2
    2.26
    -
    2.25
    6
    2.16
    ers
    2.15
    ab
    2.12
    ics
    2.11
    ary
    2.09
    5
    2.09
    POSITIVE LOGITS
     střed
    3.11
     REGIUNI
    2.91
     výrob
    2.90
     karakteristik
    2.88
     inactivació
    2.88
     znacz
    2.83
     işaret
    2.83
     órg
    2.82
     przedsiębior
    2.81
     お知らせ
    2.80
    Activations Density 0.013%

    No Known Activations