© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7829
    Prev
    Next
    INDEX
    Explanations

    grounding and related concepts

    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_22_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
    얀
    1.02
     години
    0.99
    가
    0.99
    тому
    0.96
     Marina
    0.95
     màn
    0.95
    Marina
    0.94
     Ec
    0.93
    блон
    0.93
    랑
    0.90
    POSITIVE LOGITS
    swell
    1.27
    breaking
    1.04
     zero
    0.97
    truth
    0.96
     stepfather
    0.93
     floor
    0.91
     Zero
    0.91
     फ्लोर
    0.91
    staff
    0.90
    зел
    0.90
    Activations Density 0.052%

    No Known Activations