© 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. 1512
    Prev
    Next
    INDEX
    Explanations

    lentils and train

    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
     polypes
    2.49
    ᾧ
    2.47
    squareup
    2.45
     যাবে
    2.43
     ngừa
    2.43
     getSchema
    2.41
    igenschaften
    2.38
    VCTarget
    2.37
    ើង
    2.37
    nt
    2.34
    POSITIVE LOGITS
    ing
    2.46
    <bos>
    2.08
    ุน
    2.06
    ों
    2.02
    orious
    1.97
    幡
    1.95
    uvi
    1.93
    レンダー
    1.90
    ل
    1.87
    ливо
    1.87
    Activations Density 0.142%

    No Known Activations