© 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. 2990
    Prev
    Next
    INDEX
    Explanations

    es de

    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
    ቻ
    2.47
    არ
    2.37
    汅
    2.18
    ashed
    2.15
     ApiResponse
    2.13
     ني
    2.12
    ჩ
    2.05
    太平洋
    2.05
    ெட்
    2.03
    pike
    1.98
    POSITIVE LOGITS
    지로
    2.52
     nhàng
    2.29
    时候
    2.20
    ysc
    2.19
    הר
    2.15
    علم
    2.15
    дные
    2.10
     Allowed
    2.07
    ⅛
    2.07
    وء
    2.05
    Activations Density 0.008%

    No Known Activations