© 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. 25742
    Prev
    Next
    INDEX
    Explanations

    there is or are

    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
    かなかった
    -1.20
     orice
    -1.13
    nappropriate
    -1.13
     necesar
    -1.13
     koniec
    -1.11
    ított
    -1.10
     všechny
    -1.09
     انتظار
    -1.06
     tajem
    -1.06
     ț
    -1.05
    POSITIVE LOGITS
     are
    2.83
     is
    2.58
     was
    2.16
     were
    1.77
    ’
    1.62
     isn
    1.61
     aren
    1.59
     wasn
    1.53
     many
    1.39
     may
    1.29
    Activations Density 0.076%

    No Known Activations