© 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. 92838
    Prev
    Next
    INDEX
    Explanations

    names starting with trent

    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
     prosím
    -0.72
    まん
    -0.69
    intang
    -0.68
    textview
    -0.68
     Strokes
    -0.66
     أحمد
    -0.66
    ᱬ
    -0.66
    SENT
    -0.65
    AndPassword
    -0.65
     zvyš
    -0.65
    POSITIVE LOGITS
     qualités
    0.83
     binoculars
    0.80
     रेखा
    0.78
    🔖
    0.76
    minos
    0.75
    🇹
    0.74
     erd
    0.74
    шает
    0.73
     nette
    0.72
    ligator
    0.72
    Activations Density 0.052%

    No Known Activations