© 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. 57608
    Prev
    Next
    INDEX
    Explanations

    would be

    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
     did
    -1.09
    DID
    -0.89
    Did
    -0.87
    did
    -0.86
     Did
    -0.82
    BV
    -0.81
    Bounding
    -0.79
    所
    -0.78
    Vin
    -0.71
     didn
    -0.71
    POSITIVE LOGITS
     será
    2.61
     be
    2.53
     будет
    2.50
     sarà
    2.09
     буде
    1.99
     יהיה
    1.89
     sería
    1.81
     serán
    1.80
     sera
    1.76
     يكون
    1.66
    Activations Density 0.095%

    No Known Activations