© 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. 10-GEMMASCOPE-RES-131K
    4. 19179
    Prev
    Next
    INDEX
    Explanations

    2 Star College Report group

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron spikes on unusually rare or domain‐specific tokens—things like acronyms, standalone numbers, and uncommon multi-syllable words (e.g. “tie,” “coat,” “beard,” “2,” “GO,” “ub”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ﺶ
    -1.52
     vuonna
    -1.30
    ﮑ
    -1.29
    Jährige
    -1.28
     вона
    -1.27
    lifford
    -1.25
     FÜR
    -1.23
    campista
    -1.23
    días
    -1.22
     terwijl
    -1.21
    POSITIVE LOGITS
     =
    1.49
    _
    1.49
     different
    1.48
    /*
    1.35
    /**
    1.32
    };
    1.31
    ţilor
    1.31
     “
    1.30
     ‘
    1.30
     различные
    1.28
    Activations Density 0.079%

    No Known Activations