© 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. 34-GEMMASCOPE-RES-131K
    7. 98202
    Prev
    Next
    INDEX
    Explanations

    ends of sentences with punctuation

    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
    especially
    -1.48
    particularly
    -1.38
     your
    -1.37
    Especially
    -1.26
    恚
    -1.21
     zwłaszcza
    -1.15
     terutama
    -1.13
     especialmente
    -1.13
     especially
    -1.11
    occasione
    -1.09
    POSITIVE LOGITS
     which
    2.61
    ?!
    2.28
    !!!
    1.91
    !!!!
    1.90
     даже
    1.84
    ?
    1.83
    !!!!!
    1.80
    ???
    1.77
     (!
    1.77
    !!
    1.76
    Activations Density 0.201%

    No Known Activations