© 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. 13118
    Prev
    Next
    INDEX
    Explanations

    splitting strings with delimiters

    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
    ा
    2.96
    ి
    2.75
    aos
    2.69
    ಿ
    2.66
    es
    2.64
    a
    2.60
    ்க்கு
    2.47
    ്ര
    2.45
    й
    2.45
     LICENSE
    2.42
    POSITIVE LOGITS
    tenance
    3.86
    ters
    3.51
    niak
    3.19
    tain
    2.96
    tdown
    2.93
    LaunchScheme
    2.91
    ting
    2.78
    ty
    2.65
    tyn
    2.64
    mul
    2.62
    Activations Density 0.006%

    No Known Activations