© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58221
    Prev
    Next
    INDEX
    Explanations

    Psycho-, Pharma-, AIR-

    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
     Condol
    -0.79
     مرکز
    -0.76
     Arif
    -0.75
    мб
    -0.75
    Fuk
    -0.75
    变量
    -0.71
    ;\;
    -0.71
    árol
    -0.70
    равда
    -0.70
     IPCC
    -0.70
    POSITIVE LOGITS
     autos
    1.00
     matches
    0.95
     compartil
    0.86
     Project
    0.84
     confirmed
    0.83
    tested
    0.83
     triang
    0.82
    getProject
    0.81
    recent
    0.81
     chromosome
    0.80
    Activations Density 0.013%

    No Known Activations