© 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. 13-GEMMASCOPE-2-RES-16K
    7. 9560
    Prev
    Next
    INDEX
    Explanations

    interval between things

    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_13_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
    onRouteChange
    2.32
    (*(
    2.22
    ecal
    1.97
    𝒾
    1.97
     …….
    1.95
     estad
    1.95
    ('\\
    1.85
    νο
    1.84
    webtoken
    1.83
     kali
    1.83
    POSITIVE LOGITS
    Descripcion
    2.30
    一块
    2.02
     prismatic
    1.98
    setType
    1.91
    Yesterday
    1.91
    cran
    1.90
    মধ্য
    1.90
    .")]
    1.88
    Sides
    1.86
    োহিত
    1.84
    Activations Density 0.128%

    No Known Activations