© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8955
    Prev
    Next
    INDEX
    Explanations

    tracking different aspects

    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
     delicios
    1.38
     zelen
    1.29
     modificación
    1.27
    硃
    1.26
     sabor
    1.25
    лада
    1.25
     популярных
    1.23
    ญี่ปุ่น
    1.22
     watermelon
    1.22
     ﺍ
    1.21
    POSITIVE LOGITS
    yler
    1.22
    eler
    1.19
    iletto
    1.14
    oting
    1.14
    -]
    1.13
    sys
    1.12
    imit
    1.12
     Scal
    1.10
    kiyor
    1.10
    etric
    1.10
    Activations Density 0.000%

    No Known Activations