© 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. 66109
    Prev
    Next
    INDEX
    Explanations

    Thursday dates

    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
    <td>
    -3.08
     was
    -2.81
    !!!!!!
    -2.63
    ’:
    -2.44
     shoved
    -2.28
    蹌
    -2.27
    ="
    -2.25
    ؛
    -2.23
    j
    -2.22
    や
    -2.20
    POSITIVE LOGITS
    '
    2.88
     
    2.70
     essentials
    2.27
    滹
    2.17
     elusive
    2.17
     oficialmente
    2.17
     unparalleled
    2.16
     automáticamente
    2.14
     unsere
    2.13
    いただいた
    2.09
    Activations Density 0.001%

    No Known Activations