© 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. 13-GEMMASCOPE-2-RES-16K
    7. 16355
    Prev
    Next
    INDEX
    Explanations

    anyone to

    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_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
    ->
    0.90
     SDI
    0.90
     тай
    0.84
    Dubai
    0.84
    PPI
    0.82
     Zurich
    0.82
    Duration
    0.81
     giz
    0.81
    >&
    0.80
    ร่าง
    0.80
    POSITIVE LOGITS
    æk
    1.20
     studierte
    1.17
     botanique
    1.06
    ンスター
    1.04
     安心
    1.03
     администрации
    1.02
    équilibre
    1.02
     यांच्या
    1.01
    ỹ
    1.00
    ナー
    1.00
    Activations Density 0.022%

    No Known Activations