© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2256
    Prev
    Next
    INDEX
    Explanations

    reporting issues and activity

    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
    కు
    2.47
    ்க
    2.46
    ು
    2.27
    sill
    2.25
    ers
    2.16
    ̆
    2.11
    ष्‍ट्र
    2.08
    ्‍य
    2.07
    ்ய
    2.06
    ين
    2.04
    POSITIVE LOGITS
    reactivex
    3.75
    WebV
    3.50
    ごと
    3.22
    леку
    2.98
    Չ
    2.91
    霭
    2.91
     えっと
    2.90
    ｆ
    2.88
    𝚏
    2.86
    $\,.
    2.85
    Activations Density 0.156%

    No Known Activations