© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102491
    Prev
    Next
    INDEX
    Explanations

    following disclaimer

    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
     artesanal
    -0.82
     salas
    -0.82
     interruptor
    -0.79
    tacts
    -0.79
    natured
    -0.79
    measurement
    -0.78
    RAINE
    -0.76
     augmente
    -0.76
     every
    -0.75
    TagName
    -0.73
    POSITIVE LOGITS
     zuge
    0.92
     منذ
    0.88
     interfacial
    0.81
    lalom
    0.81
     Werte
    0.78
     values
    0.78
     isotropic
    0.78
     koi
    0.76
     atrium
    0.76
     HOG
    0.75
    Activations Density 0.002%

    No Known Activations