© 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. 34-GEMMASCOPE-RES-131K
    7. 80958
    Prev
    Next
    INDEX
    Explanations

    seeing this

    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
     Fig
    -1.54
     Figure
    -1.51
    Fig
    -1.49
    Figure
    -1.47
    FIGURE
    -1.25
     Figs
    -1.09
     This
    -1.00
     July
    -0.98
     There
    -0.93
     n
    -0.93
    POSITIVE LOGITS
    大人気
    1.04
    itado
    1.03
    たまたま
    0.96
     ingredi
    0.96
    erdings
    0.96
    <b>
    0.95
    私たちは
    0.94
     consommer
    0.94
    Hilsen
    0.94
     proteine
    0.93
    Activations Density 0.000%

    No Known Activations