© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13572
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    ektor
    1.27
     anos
    1.06
     ayam
    1.02
    ̍
    1.01
     ng
    1.00
    ந்தில்
    1.00
    idenav
    0.98
     jelas
    0.98
     ekstra
    0.97
     kul
    0.97
    POSITIVE LOGITS
    ᅩ
    1.26
    ного
    1.26
    কের
    1.20
    𝗼
    1.19
    ്യാ
    1.19
     eagerly
    1.19
     гром
    1.18
     Κ
    1.18
    ocracy
    1.17
    initComponents
    1.16
    Activations Density 0.069%

    No Known Activations