© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3152
    Prev
    Next
    INDEX
    Explanations

    result within a box

    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
    ˜</
    2.59
    ยายน
    2.57
    ProxyAgent
    2.54
    驒
    2.50
    レーター
    2.48
    ᒻ
    2.42
    ﮔ
    2.41
    Просе
    2.37
     કારણે
    2.36
    Cw
    2.32
    POSITIVE LOGITS
    ीट
    2.45
    ates
    2.33
    deb
    2.31
    തര
    2.20
    बाजी
    2.19
     clicks
    2.17
    nett
    2.17
    ﺪ
    2.17
    டித்த
    2.17
    ten
    2.13
    Activations Density 0.002%

    No Known Activations