© 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. 34-GEMMASCOPE-RES-131K
    7. 117224
    Prev
    Next
    INDEX
    Explanations

    start of clauses or studies

    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
     Investigaciones
    -0.88
    гато
    -0.84
    kening
    -0.81
    ANSAS
    -0.78
     Estudios
    -0.76
    北海道
    -0.76
    笈
    -0.76
    ленной
    -0.75
     Erben
    -0.75
    верное
    -0.74
    POSITIVE LOGITS
     primeras
    0.81
     attenuation
    0.78
    fout
    0.78
    ştir
    0.75
     AlertDialog
    0.74
     uscire
    0.73
    accountId
    0.72
     zależności
    0.72
    gelopen
    0.72
    joo
    0.71
    Activations Density 0.071%

    No Known Activations