© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 804
    Prev
    Next
    INDEX
    Explanations

    core followed by central idea

    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
    gameObjects
    1.99
     pequeños
    1.94
     pequenas
    1.90
     Creating
    1.89
     गेंदों
    1.88
    り
    1.88
     Create
    1.87
     eels
    1.86
    UIS
    1.86
    lič
    1.85
    POSITIVE LOGITS
    ీ
    2.22
    此之外
    2.17
    tilt
    2.07
    mage
    1.96
    tas
    1.90
     useAppContext
    1.90
    ständig
    1.88
    t
    1.87
    悴
    1.86
    주고
    1.84
    Activations Density 0.500%

    No Known Activations