© 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. 1704
    Prev
    Next
    INDEX
    Explanations

    transparent covers

    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
     تن
    0.99
     не
    0.97
     henüz
    0.97
     universitario
    0.97
     gagal
    0.96
     کر
    0.95
     centrum
    0.95
     斜
    0.95
    वासी
    0.95
     hè
    0.95
    POSITIVE LOGITS
    দের
    1.09
    atot
    1.03
    স্তাফ
    0.99
    sé
    0.98
    sr
    0.97
    ቸውን
    0.97
    snippets
    0.97
    aise
    0.96
    ductor
    0.94
    nce
    0.92
    Activations Density 0.141%

    No Known Activations