© 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. 104256
    Prev
    Next
    INDEX
    Explanations

    criticism or negative action

    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
     If
    -1.59
     provides
    -1.51
     arguably
    -1.46
    喫
    -1.45
     Are
    -1.45
     With
    -1.41
    。
    -1.38
    <h3>
    -1.38
    The
    -1.36
    !
    -1.35
    POSITIVE LOGITS
    戋
    1.68
     nowe
    1.50
     FOLLOWING
    1.43
    ientras
    1.40
    蔸
    1.38
     unſ
    1.38
    ῞
    1.36
     generell
    1.34
     toa
    1.34
     нашел
    1.34
    Activations Density 0.023%

    No Known Activations