© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3605
    Prev
    Next
    INDEX
    Explanations

    into, in, en, open

    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
    to
    2.34
    ">,</
    1.99
     inhabitants
    1.99
    setProperty
    1.89
     сохра
    1.88
     прогно
    1.86
    sho
    1.85
     хра
    1.84
    в
    1.83
    ප්
    1.83
    POSITIVE LOGITS
    elben
    1.98
     Neben
    1.90
     solchen
    1.89
    zerű
    1.88
     enormes
    1.87
     solche
    1.84
     Umum
    1.83
     zusätzliche
    1.82
     bisschen
    1.80
     Dank
    1.74
    Activations Density 0.137%

    No Known Activations