© 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. 13-GEMMASCOPE-2-RES-16K
    7. 12123
    Prev
    Next
    INDEX
    Explanations

    e-commerce links and product names

    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_13_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
     amore
    2.22
    रोवर
    2.08
    ignores
    1.98
    俭
    1.95
     appreciating
    1.85
    犸
    1.81
     …
    1.79
    ณี
    1.78
    ित
    1.77
    ettek
    1.75
    POSITIVE LOGITS
    gll
    2.35
    gium
    2.16
    ttes
    2.16
    ijke
    2.15
    tr
    2.12
    ய்ப்ப
    2.11
    kuk
    2.11
    ப்பிர
    2.10
    Ob
    2.08
    teral
    2.07
    Activations Density 0.111%

    No Known Activations