© 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. 10-GEMMASCOPE-RES-131K
    7. 102751
    Prev
    Next
    INDEX
    Explanations

    recite truth, orders, job

    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_10/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
     siquiera
    -1.30
    нией
    -1.30
    ("")){
    -1.25
    ﻝ
    -1.20
    ："
    -1.19
    ：
    -1.19
    Beskrivning
    -1.18
     можете
    -1.18
     magyar
    -1.17
     („
    -1.16
    POSITIVE LOGITS
     what
    1.70
     it
    1.65
     not
    1.53
     because
    1.42
     rather
    1.34
     It
    1.32
     those
    1.27
     who
    1.26
    viaje
    1.24
     current
    1.19
    Activations Density 0.076%

    No Known Activations