© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13567
    Prev
    Next
    INDEX
    Explanations

    topics or abstract conceptspreços, prices, stock, sales

    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
    只需要
    1.38
     理
    1.35
     持
    1.30
     길이가
    1.28
     نرم
    1.24
     evaporate
    1.24
    ත්ම
    1.20
     방법에
    1.19
     る
    1.18
     到
    1.18
    POSITIVE LOGITS
    gid
    1.44
    ié
    1.39
    ség
    1.32
    icida
    1.32
    sd
    1.30
    eo
    1.30
    gay
    1.28
    dU
    1.27
    gio
    1.26
     noite
    1.26
    Activations Density 0.000%

    No Known Activations