© 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. 2855
    Prev
    Next
    INDEX
    Explanations

    numbers, codes, and street names

    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
     maybe
    -0.84
    为大家
    -0.79
     ребен
    -0.76
    ######
    -0.76
     Flowers
    -0.74
     her
    -0.73
     mora
    -0.73
    См
    -0.73
    SignUp
    -0.71
    ()">
    -0.71
    POSITIVE LOGITS
     उदाहरण
    0.85
    ilà
    0.82
    reportError
    0.81
     ensembles
    0.79
     reprints
    0.79
    suri
    0.78
    句話
    0.77
     Tight
    0.75
     represent
    0.75
    blowing
    0.74
    Activations Density 0.042%

    No Known Activations