© 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
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 710
    Prev
    Next
    INDEX
    Explanations

    sentence correctness and pluralization

    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
    ביע
    3.12
    ్యాచ్
    3.09
    ্শন
    3.07
    elementProp
    3.04
    prefab
    2.82
    𠃌
    2.82
    γωγ
    2.79
    ombrie
    2.79
    ÇÃO
    2.78
    唆
    2.78
    POSITIVE LOGITS
    णिज्य
    3.77
    onload
    3.01
    स्थ्य
    2.87
    es
    2.79
     tuf
    2.57
    ahoo
    2.53
    etting
    2.53
    inger
    2.51
    enden
    2.46
     w
    2.45
    Activations Density 4.567%

    No Known Activations