© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 1787
    Prev
    Next
    INDEX
    Explanations

    language and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ا
    0.38
    a
    0.38
    、「
    0.36
    ي
    0.36
    ی
    0.35
     hanno
    0.35
     Са
    0.35
    u
    0.34
    ють
    0.34
    اگر
    0.33
    POSITIVE LOGITS
     phrases
    0.57
     spoken
    0.52
    tion
    0.51
     palavras
    0.51
     bahasa
    0.50
     frases
    0.49
     words
    0.49
     Bahasa
    0.48
     Phrases
    0.48
     язык
    0.47
    Activations Density 1.325%

    No Known Activations