© 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. 22-GEMMASCOPE-RES-131K
    7. 24975
    Prev
    Next
    INDEX
    Explanations

    financial figures and codes

    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
    Negative Logits
     aranha
    -1.16
     farol
    -1.16
     sportif
    -1.14
    jauh
    -1.10
    anggaran
    -1.08
    detek
    -1.08
     alkohol
    -1.05
     internetu
    -1.05
     alkoh
    -1.05
    fokus
    -1.04
    POSITIVE LOGITS
    J
    0.96
    uch
    0.95
    L
    0.93
     иногда
    0.90
    con
    0.88
    l
    0.88
    M
    0.87
    ar
    0.85
    ile
    0.85
     goddamn
    0.84
    Activations Density 0.017%

    No Known Activations