© 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. 3220
    Prev
    Next
    INDEX
    Explanations

    resources for further

    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
    Hozzáférés
    1.27
    s
    1.20
    ments
    1.17
    nt
    1.15
    "-
    1.14
     ."
    1.14
    nya
    1.13
    .."
    1.11
    „
    1.09
    "*
    1.07
    POSITIVE LOGITS
    OrCallback
    2.08
     Επι
    2.05
     wcex
    1.99
     perspiciatis
    1.95
     Luật
    1.94
    τία
    1.93
     })),
    1.93
     legislação
    1.93
    穹
    1.93
     Màu
    1.92
    Activations Density 0.199%

    No Known Activations