© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12745
    Prev
    Next
    INDEX
    Explanations

    bib references

    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
     felpa
    -1.19
     lustige
    -1.07
    abbé
    -1.05
     concetto
    -1.00
     trecut
    -0.99
    annah
    -0.97
     realidade
    -0.97
    ⿻
    -0.96
    ダイソー
    -0.96
     Tn
    -0.95
    POSITIVE LOGITS
     for
    1.18
     to
    1.18
     now
    1.05
    _
    1.04
     kini
    1.02
     дър
    0.97
     diesem
    0.96
     when
    0.93
     #
    0.91
     diese
    0.91
    Activations Density 0.080%

    No Known Activations