© 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. 68658
    Prev
    Next
    INDEX
    Explanations

    origin or background

    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
     things
    -1.12
    ecé
    -1.11
    理由は
    -1.09
     during
    -1.09
    内容は
    -1.04
    职责
    -1.03
     könne
    -1.02
    儼
    -1.02
    žnost
    -1.01
     projected
    -1.00
    POSITIVE LOGITS
     from
    1.91
     backgrounds
    1.23
    awancara
    1.05
     whence
    1.04
     chauss
    1.03
     знаем
    0.99
     FROM
    0.98
     ám
    0.98
     background
    0.97
    出自
    0.97
    Activations Density 0.056%

    No Known Activations