© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 20539
    Prev
    Next
    INDEX
    Explanations

    article and related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    措
    0.43
    pairwise
    0.41
    Third
    0.38
    Networking
    0.37
    时的
    0.36
    inheritDoc
    0.36
    silyl
    0.36
     mẽ
    0.36
    subs
    0.35
    ሖ
    0.35
    POSITIVE LOGITS
     artículos
    0.56
     artículo
    0.50
     articles
    0.48
     article
    0.48
    ్రహ్
    0.47
    Article
    0.47
     artigos
    0.47
     molécules
    0.46
     artikkel
    0.46
     comentários
    0.45
    Activations Density 0.000%

    No Known Activations