© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68357
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by good wishes

    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_22/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
     therefore
    -1.20
     donc
    -1.13
    therefore
    -1.06
     impuls
    -0.94
     actrice
    -0.90
    thus
    -0.90
    mentaux
    -0.90
     casquette
    -0.90
    ſus
    -0.90
     alors
    -0.88
    POSITIVE LOGITS
     will
    1.11
     должна
    1.02
     pioggia
    0.91
    できれば
    0.90
     until
    0.88
     below
    0.88
     particolar
    0.86
    They
    0.86
     they
    0.84
     også
    0.84
    Activations Density 0.019%

    No Known Activations