© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83975
    Prev
    Next
    INDEX
    Explanations

    Jafar, CF, ZF, phyr

    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
     према
    -0.90
     greener
    -0.80
     BERT
    -0.75
     beyond
    -0.75
    OSX
    -0.74
    keycode
    -0.73
    Wc
    -0.73
     ionizing
    -0.73
    itant
    -0.73
     Missile
    -0.73
    POSITIVE LOGITS
    ANCA
    0.81
     densities
    0.73
     мест
    0.66
    抵
    0.65
    Detective
    0.65
     пор
    0.62
    悩
    0.61
    veu
    0.60
    letch
    0.60
    관
    0.60
    Activations Density 0.043%

    No Known Activations