© 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. 111183
    Prev
    Next
    INDEX
    Explanations

    I and what I possess

    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
    ӧ
    -1.81
    เพราะ
    -1.78
     gustaMe
    -1.70
     wirklich
    -1.68
    鉺
    -1.67
    ቺ
    -1.64
    申し訳
    -1.61
    say
    -1.58
    锇
    -1.58
     unſ
    -1.57
    POSITIVE LOGITS
     including
    2.22
     both
    2.08
     includes
    1.99
     those
    1.95
     their
    1.93
     encompasses
    1.76
     has
    1.75
     embodies
    1.75
     a
    1.74
     would
    1.70
    Activations Density 0.023%

    No Known Activations