© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 506
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sogenannten
    2.12
     Curso
    2.04
     পাওয়
    2.02
     Ecusson
    2.00
     algoritmo
    1.98
     funzionamento
    1.97
    ፡
    1.89
    চলিত
    1.88
     remarqué
    1.87
     mecanismo
    1.86
    POSITIVE LOGITS
     integrity
    1.40
    ele
    1.39
     nearest
    1.32
    eurs
    1.31
     groups
    1.27
     rooms
    1.25
    boards
    1.24
    -
    1.23
     near
    1.21
    ores
    1.21
    Activations Density 10.405%

    No Known Activations