© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39061
    Prev
    Next
    INDEX
    Explanations

    past tense actions or states

    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
     disponíveis
    -1.08
    مرة
    -1.00
    quê
    -1.00
    Commande
    -0.98
    *)&
    -0.98
    شهاد
    -0.96
     disediakan
    -0.95
     verkle
    -0.91
     necessários
    -0.91
    ֝
    -0.90
    POSITIVE LOGITS
     that
    1.77
     from
    1.77
     which
    1.46
     whose
    1.33
     for
    1.26
     που
    1.15
     including
    1.13
    :
    1.10
     namely
    1.10
     relating
    1.05
    Activations Density 0.095%

    No Known Activations