© 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. 44994
    Prev
    Next
    INDEX
    Explanations

    words following conjunctions or 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_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
     μεταξύ
    0.49
     प्रवृत्ति
    0.47
     ယ
    0.46
     χω
    0.45
     過
    0.44
     après
    0.44
     ଅ
    0.43
     ਵ
    0.43
     ಮೇ
    0.43
     বক্স
    0.43
    POSITIVE LOGITS
    flor
    0.53
     violators
    0.49
    спе
    0.46
     antico
    0.45
    низ
    0.45
    Ви
    0.44
    שהו
    0.44
    Ве
    0.43
     idioma
    0.42
    วิน
    0.42
    Activations Density 0.000%

    No Known Activations