© 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. 13054
    Prev
    Next
    INDEX
    Explanations

    numbered lists

    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
    따
    2.15
    틱
    2.01
    깐
    1.95
    ਨੀ
    1.83
    رید
    1.83
    وم
    1.82
    holz
    1.81
    đe
    1.81
    ਸੀ
    1.78
    LowerCase
    1.77
    POSITIVE LOGITS
    eris
    2.42
    quela
    2.35
    er
    2.28
    eenth
    2.26
    tanto
    2.20
    வரது
    2.19
    mares
    2.19
    加坡
    2.19
    ي
    2.16
    erus
    2.16
    Activations Density 0.014%

    No Known Activations