© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127816
    Prev
    Next
    INDEX
    Explanations

    best followed by nouns

    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
    isierte
    -1.70
    寘
    -1.46
     kontaktu
    -1.46
    蚰
    -1.45
    茀
    -1.45
    亖
    -1.44
    ujemy
    -1.40
    ൎ
    -1.38
    ifers
    -1.38
    loves
    -1.36
    POSITIVE LOGITS
     where
    1.66
     when
    1.64
     it
    1.52
     even
    1.51
     who
    1.47
     only
    1.39
    er
    1.34
    不需要
    1.31
    d
    1.25
     few
    1.23
    Activations Density 0.028%

    No Known Activations