© 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. 84556
    Prev
    Next
    INDEX
    Explanations

    word meanings and origins

    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
     de
    -1.00
     like
    -0.97
     piattaforma
    -0.96
     націона
    -0.94
     wystarczy
    -0.90
     services
    -0.85
     гостиной
    -0.85
     diferite
    -0.85
     zostanie
    -0.84
     ovviamente
    -0.84
    POSITIVE LOGITS
     tillegg
    1.16
     évêque
    1.00
     bluse
    0.96
    бр
    0.90
    駅から
    0.89
     beina
    0.88
    }")]
    0.88
     betyder
    0.87
     означа
    0.86
     betyr
    0.85
    Activations Density 0.022%

    No Known Activations