© 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. 47756
    Prev
    Next
    INDEX
    Explanations

    defining or denoting something

    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
    tymologie
    -0.85
     praising
    -0.84
    indakan
    -0.82
    versial
    -0.80
     connus
    -0.79
     oorsp
    -0.79
     exemplifies
    -0.79
    saucony
    -0.79
     Avez
    -0.79
    そうです
    -0.78
    POSITIVE LOGITS
     denoted
    4.38
     labeled
    3.27
     labelled
    3.23
    labeled
    2.59
     marked
    2.59
     обозна
    2.53
     represented
    2.48
     designated
    2.45
    labelled
    2.45
     ozna
    2.23
    Activations Density 0.193%

    No Known Activations