© 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. 22-GEMMASCOPE-RES-131K
    7. 34519
    Prev
    Next
    INDEX
    Explanations

    is followed by decided or located

    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_22/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
    convertView
    -0.99
    部は
    -0.90
    безпе
    -0.84
     Then
    -0.80
     Hivatalos
    -0.79
    věd
    -0.79
     anota
    -0.78
    arshal
    -0.78
    ConfigFile
    -0.78
     his
    -0.78
    POSITIVE LOGITS
     enfermos
    0.82
    Carex
    0.79
     OGSÅ
    0.78
     gerichtet
    0.76
    León
    0.75
     fijar
    0.75
     squeak
    0.75
    pses
    0.75
    amoto
    0.74
    UNG
    0.73
    Activations Density 0.191%

    No Known Activations