© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1181
    Prev
    Next
    INDEX
    Explanations

    phrases involving words

    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
     quizzes
    -0.84
    Write
    -0.83
    ynomial
    -0.77
     Invo
    -0.76
     radiators
    -0.74
    größern
    -0.73
    chriften
    -0.71
     Canucks
    -0.71
    uuml
    -0.71
     وفا
    -0.71
    POSITIVE LOGITS
     words
    6.28
    words
    3.92
    Words
    3.67
     Words
    3.67
     palabras
    3.23
     слова
    3.19
     WORDS
    3.03
    WORDS
    2.97
     woorden
    2.75
     palavras
    2.70
    Activations Density 0.046%

    No Known Activations