© 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. 14694
    Prev
    Next
    INDEX
    Explanations

    ACE, YAKE!, Core Data, Carbon Brief

    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
    蜍
    2.84
    鸯
    2.84
    netje
    2.55
    鴦
    2.50
    蕉
    2.42
    Geplaatst
    2.40
    纫
    2.38
    बान
    2.32
    UE
    2.26
    eways
    2.23
    POSITIVE LOGITS
    er
    3.00
    м
    2.55
    𝙘
    2.52
    𝙠
    2.46
    ilung
    2.45
    에
    2.43
    i
    2.42
    ه
    2.41
    нский
    2.39
    ॉप
    2.37
    Activations Density 0.011%

    No Known Activations