© 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. 97936
    Prev
    Next
    INDEX
    Explanations

    presiding, appellant, form

    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
     stylu
    -0.73
    /**/
    -0.70
    orge
    -0.69
     בישראל
    -0.69
    Lots
    -0.68
     Solidar
    -0.68
    EDAD
    -0.67
    OMO
    -0.66
     HOS
    -0.65
    ꒰
    -0.65
    POSITIVE LOGITS
     impreg
    0.75
    _+
    0.73
     Corbett
    0.73
    MCU
    0.72
     Benedict
    0.72
    Benedict
    0.71
     uncons
    0.70
     dyn
    0.69
     ECS
    0.69
     MCU
    0.69
    Activations Density 0.025%

    No Known Activations