© 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. 10-GEMMASCOPE-RES-131K
    7. 28968
    Prev
    Next
    INDEX
    Explanations

    on or after January

    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_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
    ⛄
    -1.59
     ressort
    -1.58
    .”
    -1.58
    😓
    -1.52
    <bos>
    -1.50
     @__
    -1.48
    zed
    -1.47
     цвят
    -1.45
     рассказала
    -1.45
     provocando
    -1.45
    POSITIVE LOGITS
     it
    1.95
     said
    1.74
     the
    1.65
    瞜
    1.63
     proudly
    1.62
     steeped
    1.53
    ズニー
    1.51
     contrasting
    1.51
     que
    1.48
     were
    1.48
    Activations Density 0.005%

    No Known Activations