© 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. 94102
    Prev
    Next
    INDEX
    Explanations

    scene graph, Warren Brown, German tanker, Intel, XML

    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
     узна
    -0.79
    なあ
    -0.75
     fotográfica
    -0.71
    それぞれの
    -0.71
    的话
    -0.70
     hilft
    -0.70
     indiv
    -0.70
    atterns
    -0.69
    ultan
    -0.69
     vergeben
    -0.69
    POSITIVE LOGITS
    ærk
    0.86
    '-'
    0.82
     bounding
    0.82
    %?
    0.81
    :''
    0.80
    Bounding
    0.79
     Ogre
    0.79
    "^
    0.79
    Ireland
    0.79
     scene
    0.79
    Activations Density 0.047%

    No Known Activations