© 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. 33635
    Prev
    Next
    INDEX
    Explanations

    refer to

    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
    lege
    -0.91
    ⇐
    -0.85
     Lor
    -0.84
    ciona
    -0.84
    criminate
    -0.81
    estimable
    -0.81
    tice
    -0.81
     sè
    -0.80
     kell
    -0.79
     immagine
    -0.79
    POSITIVE LOGITS
    <b>
    0.94
     хорошая
    0.81
    Conclusions
    0.78
     erfü
    0.77
     behaup
    0.77
     wohn
    0.72
    bbons
    0.71
    ními
    0.71
     erzählen
    0.69
     хорошее
    0.69
    Activations Density 0.005%

    No Known Activations