© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64868
    Prev
    Next
    INDEX
    Explanations

    XML/Maven dependency tags

    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
     Præ
    -0.90
    кою
    -0.73
     ajudar
    -0.73
     preservar
    -0.72
     attracted
    -0.72
     aliviar
    -0.72
    cloak
    -0.71
    dities
    -0.69
     adaptarse
    -0.69
     argue
    -0.69
    POSITIVE LOGITS
    bom
    1.07
     core
    0.94
    core
    0.85
    Čes
    0.82
     ää
    0.81
     library
    0.81
     pocit
    0.81
    Osob
    0.81
     garanti
    0.80
    CORE
    0.80
    Activations Density 0.072%

    No Known Activations