© 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. 22-GEMMASCOPE-RES-131K
    7. 15142
    Prev
    Next
    INDEX
    Explanations

    article followed by descriptive word

    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_22/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
    あぁ
    -1.54
     alza
    -1.53
     lampa
    -1.52
     romantis
    -1.48
     kenal
    -1.46
    えっ
    -1.45
    って何
    -1.41
     akrab
    -1.41
     mosca
    -1.38
     inginkan
    -1.38
    POSITIVE LOGITS
     котором
    1.45
     \%$
    1.25
     которых
    1.18
    <bos>
    1.17
    つまり
    1.17
    須賀
    1.15
     áng
    1.15
     néz
    1.09
    もあった
    1.09
     view
    1.08
    Activations Density 0.055%

    No Known Activations