© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56962
    Prev
    Next
    INDEX
    Explanations

    first person recounting actions or discoveries

    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
     السياس
    -1.03
     ardından
    -0.88
    prende
    -0.87
     сказали
    -0.85
    Eglise
    -0.85
     dropdown
    -0.84
    DetailComponent
    -0.84
    codename
    -0.84
    lulu
    -0.84
    badan
    -0.83
    POSITIVE LOGITS
     created
    1.34
     wrote
    1.30
     spent
    1.19
     experimenting
    1.09
     use
    1.09
     found
    1.08
     create
    1.01
    proto
    0.99
     spend
    0.95
     littered
    0.94
    Activations Density 0.268%

    No Known Activations