© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107394
    Prev
    Next
    INDEX
    Explanations

    comma followed by "I" or "it"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ikke
    -1.30
     nicht
    -1.22
     Yeah
    -1.14
     Tidak
    -1.13
    哦
    -1.11
    》,
    -1.05
     не
    -1.05
     belum
    -1.05
     blah
    -1.02
    آیا
    -1.02
    POSITIVE LOGITS
     but
    2.31
     that
    1.87
     exactly
    1.76
     definitely
    1.59
     it
    1.58
     agreed
    1.45
    but
    1.45
     except
    1.44
     absolutely
    1.41
     indeed
    1.40
    Activations Density 0.013%

    No Known Activations