© 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. 40-GEMMASCOPE-2-RES-262K
    7. 133020
    Prev
    Next
    INDEX
    Explanations

    grammatical context with nouns

    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_40_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
    ṅ
    0.38
    ዑ
    0.37
     கா
    0.36
     एक्टिव
    0.36
    母
    0.36
    rep
    0.36
    ታት
    0.35
     ކ
    0.35
    Zu
    0.35
    ル
    0.35
    POSITIVE LOGITS
     rosas
    0.41
    IVACON
    0.41
     לפני
    0.41
     leis
    0.39
     Надо
    0.38
    उचर
    0.38
    を示す
    0.38
    শন
    0.38
     концер
    0.38
    শান
    0.38
    Activations Density 0.000%

    No Known Activations