© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14999
    Prev
    Next
    INDEX
    Explanations

    pivot =

    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
    ไม่
    1.55
    นำ
    1.40
    測
    1.38
    ตาม
    1.38
     manqu
    1.34
     पण
    1.34
    ท
    1.33
     Solving
    1.33
    et
    1.31
    Dangerous
    1.28
    POSITIVE LOGITS
    ྂ
    1.89
    rophenyl
    1.84
    ǫ
    1.84
    yj
    1.84
    anoate
    1.77
     larvae
    1.77
    िरपेक्ष
    1.75
    ternut
    1.74
    iewicz
    1.73
    此同时
    1.71
    Activations Density 0.079%

    No Known Activations