© 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. 35589
    Prev
    Next
    INDEX
    Explanations

    email addresses and names

    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
    áska
    -1.13
    %;
    -1.05
     kæ
    -1.00
    ODO
    -0.98
    _;
    -0.97
    fact
    -0.96
     What
    -0.96
    ⩽
    -0.95
    bra
    -0.94
    $),
    -0.92
    POSITIVE LOGITS
     poète
    1.09
    깡
    1.09
    nhung
    1.08
     paliwa
    1.07
    Postup
    1.07
    livro
    1.07
    焢
    1.06
    Karakter
    1.04
    Kapitel
    1.03
     gekauft
    1.02
    Activations Density 0.010%

    No Known Activations