© 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. 60678
    Prev
    Next
    INDEX
    Explanations

    there is/was

    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
     no
    -1.43
     fewer
    -1.41
     keine
    -1.16
    なんですよ
    -1.10
     were
    -1.09
     weren
    -1.09
     aren
    -1.05
     नहीं
    -0.98
     никаких
    -0.97
     değil
    -0.96
    POSITIVE LOGITS
     is
    2.92
     есть
    1.63
     είναι
    1.26
     Is
    1.14
    เป็น
    1.02
     هست
    1.01
    是
    1.01
     was
    1.01
    is
    0.97
    的是
    0.96
    Activations Density 0.074%

    No Known Activations