© 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. 13945
    Prev
    Next
    INDEX
    Explanations

    SQL table definitions with column names

    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
    ی
    2.98
    ˏ
    2.79
    ठान
    2.71
    ъ
    2.66
    ्याय
    2.63
    getCurrent
    2.48
    et
    2.45
    $('
    2.42
     toys
    2.40
    InChildren
    2.40
    POSITIVE LOGITS
    此之外
    3.22
    tan
    3.08
    ffin
    2.66
    lgan
    2.65
    tar
    2.60
    нном
    2.59
    t
    2.57
    gars
    2.48
    tk
    2.42
    dison
    2.41
    Activations Density 0.018%

    No Known Activations