© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92489
    Prev
    Next
    INDEX
    Explanations

    discussion about forums

    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_34/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
     мене
    -1.09
    meros
    -1.05
     необходимо
    -1.05
     festen
    -1.02
     vielleicht
    -1.02
    rinhos
    -1.02
    your
    -1.00
    鼠标
    -1.00
    </b>
    -0.98
     speaking
    -0.98
    POSITIVE LOGITS
     about
    1.70
     of
    1.24
     on
    1.23
    げた
    1.15
     forum
    1.09
    <bos>
    1.05
     gesloten
    1.03
    そうに
    1.02
     forums
    0.99
    [{
    0.97
    Activations Density 0.015%

    No Known Activations