© 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. 66164
    Prev
    Next
    INDEX
    Explanations

    daily frequency

    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
     abusos
    -1.38
    做事
    -1.33
    ooplankton
    -1.30
    摁
    -1.28
    他想
    -1.28
     détruit
    -1.27
    荸
    -1.27
    のない
    -1.26
     gosto
    -1.25
     tives
    -1.24
    POSITIVE LOGITS
    你
    1.67
     or
    1.59
    他
    1.48
     including
    1.44
    您
    1.41
    她
    1.38
     following
    1.34
     your
    1.34
    年
    1.34
     incluindo
    1.30
    Activations Density 0.029%

    No Known Activations