© 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. 10592
    Prev
    Next
    INDEX
    Explanations

    source code

    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
    ের
    1.81
    cape
    1.76
    anud
    1.61
    es
    1.59
    র
    1.58
    ു
    1.56
    cane
    1.55
    ی
    1.53
    পত্রে
    1.49
    ہ
    1.48
    POSITIVE LOGITS
    ெல்ல
    1.42
     dig
    1.41
    ﺶ
    1.40
     꺼
    1.35
     months
    1.35
     ου
    1.35
     int
    1.34
     seg
    1.33
     ch
    1.32
     મહિના
    1.32
    Activations Density 9.713%

    No Known Activations