© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 10855
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    $/../../
    3.46
    性
    2.69
    రుగులు
    2.61
    sklearn
    2.61
    ی
    2.61
     officinalis
    2.58
    性の
    2.56
    тавли
    2.55
    ї
    2.55
     Raton
    2.54
    POSITIVE LOGITS
    ۰۰
    2.73
    b
    2.48
     þing
    2.41
    gar
    2.40
    emas
    2.32
    bos
    2.31
    g
    2.29
    gj
    2.27
    कार
    2.27
     ganglions
    2.26
    Activations Density 0.011%

    No Known Activations