© 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. 14844
    Prev
    Next
    INDEX
    Explanations

    most important / compelling / rare

    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
     해도
    2.00
    UGUST
    2.00
    ็ต
    2.00
     세
    1.99
    肅
    1.97
     अरो
    1.96
     closeModal
    1.95
    세를
    1.91
    넬
    1.90
    饉
    1.89
    POSITIVE LOGITS
    wa
    1.75
    ır
    1.71
    ikler
    1.71
    a
    1.70
    mo
    1.69
    counter
    1.68
    binding
    1.67
    military
    1.65
    ikti
    1.63
    l
    1.63
    Activations Density 0.000%

    No Known Activations