© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 40178
    Prev
    Next
    INDEX
    Explanations

    discovered something new

    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
     จะ
    -1.16
     cinquième
    -1.12
     your
    -1.10
    踯
    -1.09
     cimetière
    -1.08
     แท
    -1.05
    masing
    -1.05
     exemplos
    -1.04
    きましたが
    -1.02
     jogadores
    -1.00
    POSITIVE LOGITS
     by
    1.25
     Robert
    1.11
     more
    1.06
    работки
    1.06
     offers
    1.05
     Michael
    1.00
     organisations
    0.99
    ماع
    0.99
     many
    0.98
     pushes
    0.96
    Activations Density 0.038%

    No Known Activations