© 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. 10-GEMMASCOPE-RES-131K
    7. 67463
    Prev
    Next
    INDEX
    Explanations

    phrases starting clauses

    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_10/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
     will
    -2.02
     including
    -1.80
     other
    -1.74
     then
    -1.67
     become
    -1.59
     with
    -1.55
     people
    -1.54
     additional
    -1.54
     there
    -1.54
     at
    -1.54
    POSITIVE LOGITS
    brainly
    1.91
    Ū
    1.51
    ฿
    1.44
    OrNil
    1.43
    hlar
    1.42
    
    1.41
    minin
    1.41
     LCCN
    1.39
     februari
    1.37
     Chapelle
    1.36
    Activations Density 0.075%

    No Known Activations