© 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. 98417
    Prev
    Next
    INDEX
    Explanations

    traffic tickets, fines, and charges

    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
     of
    -1.18
     gunfire
    -1.05
     neque
    -1.02
     кнопку
    -1.00
     dimming
    -0.99
     secundarios
    -0.98
     pairwise
    -0.98
    IsString
    -0.98
     vinyle
    -0.97
    ILLING
    -0.96
    POSITIVE LOGITS
     penalties
    1.38
    Jeden
    1.18
    Especificações
    1.16
     crackdown
    1.11
    PUESTA
    1.10
    Ứng
    1.09
     ?$
    1.09
    ৫
    1.08
    inigungs
    1.06
     Präsidenten
    1.06
    Activations Density 0.053%

    No Known Activations